Compare commits

..
1 Commits
Author SHA1 Message Date
Georgi Gerganov 04a134c70b ci : make release workflows use a deply key 2026-08-17 09:58:11 +03:00
3212 changed files with 184827 additions and 543166 deletions
+6 -10
View File
@@ -19,15 +19,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM ${CANN_BASE_IMAGE} AS build
@@ -43,7 +40,7 @@ WORKDIR /app
# -- Copy project files --
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
# -- Set CANN environment variables (required for compilation) --
# Using ENV instead of `source` allows environment variables to persist across the entire image layer
@@ -148,7 +145,7 @@ ENTRYPOINT ["/app/tools.sh"]
# ==============================================================================
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
ENTRYPOINT [ "/app/llama-cli" ]
@@ -158,9 +155,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
HEALTHCHECK --interval=5m CMD [ "curl", "-f", "http://localhost:8080/health" ]
+10 -12
View File
@@ -1,4 +1,4 @@
ARG UBUNTU_VERSION=26.04
ARG UBUNTU_VERSION=24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
@@ -9,15 +9,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
@@ -25,13 +22,15 @@ FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
ARG TARGETARCH
RUN apt-get update && \
apt-get install -y build-essential git cmake libssl-dev
apt-get install -y gcc-14 g++-14 build-essential git cmake libssl-dev
ENV CC=gcc-14 CXX=g++-14
WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
@@ -105,7 +104,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -115,9 +114,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
+6 -13
View File
@@ -17,15 +17,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
@@ -43,7 +40,7 @@ WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
@@ -87,9 +84,6 @@ RUN apt-get update \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
# Some hosts (e.g. GKE) only mount the driver here, and CUDA 12.8.1-12.9.1 base images don't set these paths
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/nvidia/lib:${LD_LIBRARY_PATH}
COPY --from=build /app/lib/ /app
### Full
@@ -119,7 +113,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -129,9 +123,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
+19 -30
View File
@@ -1,4 +1,4 @@
ARG ONEAPI_VERSION=2026.2.0-devel-ubuntu24.04
ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
@@ -11,40 +11,32 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS build
RUN echo "Download oneDNN installation package" && \
wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/46452a4a-7b7f-49f2-be4c-602a900180bb/intel-onednn-2026.1.0.625_offline.sh -O intel-onednn_offline.sh && \
echo "Install oneDNN components" && \
bash intel-onednn_offline.sh -s -a --silent --eula accept
ARG GGML_SYCL_F16=ON
ARG LEVEL_ZERO_VERSION=1.34.0
ARG LEVEL_ZERO_VERSION=1.28.2
ARG LEVEL_ZERO_UBUNTU_VERSION=u24.04
RUN apt-get update && \
apt-get install -y git libssl-dev wget ca-certificates && \
cd /tmp && \
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/libze1_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O libze1.deb && \
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/libze-dev_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O libze-dev.deb && \
apt-get -o Dpkg::Options::="--force-overwrite" install -y ./libze1.deb ./libze-dev.deb && \
rm -f /tmp/libze1.deb /tmp/libze-dev.deb
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb && \
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb && \
apt-get -o Dpkg::Options::="--force-overwrite" install -y ./level-zero.deb ./level-zero-devel.deb && \
rm -f /tmp/level-zero.deb /tmp/level-zero-devel.deb
WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
echo "GGML_SYCL_F16 is set" \
@@ -53,7 +45,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
fi && \
echo "Building with dynamic libs" && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${OPT_SYCL_F16} && \
cmake --build build --config Release -j$((($(nproc)+1)/2))
cmake --build build --config Release -j$(nproc)
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;
@@ -82,8 +74,6 @@ LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.url=$IMAGE_URL \
org.opencontainers.image.source=$IMAGE_SOURCE
COPY --from=build /opt/intel/oneapi/dnnl /opt/intel/oneapi/dnnl
#Following versions are for multiple GPUs, since 26.x has known issue:
# https://github.com/ggml-org/llama.cpp/issues/21747,
# https://github.com/intel/compute-runtime/issues/921.
@@ -94,11 +84,11 @@ COPY --from=build /opt/intel/oneapi/dnnl /opt/intel/oneapi/dnnl
#ARG IGDGMM_VERSION=22.8.2
ARG IGC_VERSION=v2.42.6
ARG IGC_VERSION_FULL=2_2.42.6+23070
ARG COMPUTE_RUNTIME_VERSION=26.40.40196.8
ARG COMPUTE_RUNTIME_VERSION_FULL=26.40.40196.8-0
ARG IGDGMM_VERSION=22.10.2
ARG IGC_VERSION=v2.34.4
ARG IGC_VERSION_FULL=2_2.34.4+21428
ARG COMPUTE_RUNTIME_VERSION=26.18.38308.1
ARG COMPUTE_RUNTIME_VERSION_FULL=26.18.38308.1-0
ARG IGDGMM_VERSION=22.10.0
RUN mkdir /tmp/neo/ && cd /tmp/neo/ \
&& wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
&& wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
@@ -112,7 +102,7 @@ RUN mkdir /tmp/neo/ && cd /tmp/neo/ \
&& dpkg --install *.deb
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg openssl libssl-dev \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
@@ -151,7 +141,7 @@ ENTRYPOINT ["/app/tools.sh"]
FROM base AS light
COPY --from=build /app/lib/ /app
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -161,10 +151,9 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/lib/ /app
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
+11 -20
View File
@@ -1,9 +1,10 @@
ARG UBUNTU_VERSION=22.04
# This needs to generally match the container host's environment.
ARG MUSA_VERSION=rc4.3.0
# Target the MUSA build image
ARG BASE_MUSA_DEV_CONTAINER=registry.mthreads.com/mcconline/musa_sdk:5.2.0-devel-ubuntu${UBUNTU_VERSION}-s5000
ARG BASE_MUSA_DEV_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64
ARG BASE_MUSA_RUN_CONTAINER=registry.mthreads.com/mcconline/musa_sdk:5.2.0-runtime-ubuntu${UBUNTU_VERSION}-s5000
ARG BASE_MUSA_RUN_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
@@ -15,15 +16,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
@@ -39,16 +37,13 @@ RUN apt-get update && \
python3-pip \
git \
libssl-dev \
libgomp1 \
musa-mualg-5-2 \
musa-muthrust-5-2 \
libmthreads-compute
libgomp1
WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
@@ -85,16 +80,13 @@ LABEL org.opencontainers.image.created=$BUILD_DATE \
org.opencontainers.image.source=$IMAGE_SOURCE
RUN apt-get update \
&& apt-get install -y libgomp1 curl ffmpeg libmthreads-compute \
&& apt-get install -y libgomp1 curl ffmpeg \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
&& find /var/cache -type f -delete
# The MUSA runtime image does not register its library directory
RUN echo "/usr/local/musa/lib" > /etc/ld.so.conf.d/musa-runtime.conf && ldconfig
COPY --from=build /app/lib/ /app
### Full
@@ -123,7 +115,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -133,9 +125,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
+46 -143
View File
@@ -22,51 +22,27 @@
spirv-headers,
nodejs,
importNpmLock,
syclToolkit ? null,
level-zero,
ocl-icd,
intel-graphics-compiler,
intel-compute-runtime,
makeBinaryWrapper,
useBlas ?
builtins.all (x: !x) [
useCuda
useMetalKit
useRocm
useVulkan
useSycl
]
&& blas.meta.available,
useCuda ? config.cudaSupport,
useMetalKit ? stdenv.hostPlatform.isAarch64 && stdenv.hostPlatform.isDarwin,
useMetalKit ? stdenv.isAarch64 && stdenv.isDarwin,
# Increases the runtime closure size by ~700M
useMpi ? false,
useRocm ? config.rocmSupport,
rocmGpuTargets ? builtins.concatStringsSep ";" rocmPackages.clr.gpuTargets,
useVulkan ? false,
useRpc ? false,
useSycl ? false,
# Rebuild, not a runtime switch. cmake default is off.
syclF16 ? false,
# null keeps JIT. AOT makes icpx run ocloc, which DPC++ does not ship.
syclDeviceArch ? null,
syclMaxParallelLinkJobs ? null,
llamaVersion ? "0.0.0", # Arbitrary version, substituted by the flake
# CUDA needs its backend stdenv or libstdc++ mismatches downstream.
# SYCL needs icpx which is provided by the oneAPI stdenv
effectiveStdenv ?
if useCuda && useSycl then
throw "llama-cpp: useCuda and useSycl are mutually exclusive"
else if useCuda then
cudaPackages.backendStdenv
else if useSycl then
if syclToolkit == null then
throw "llama-cpp: useSycl requires syclToolkit, consider setting it to intel-oneapi-toolkit"
else
syclToolkit.stdenv
else
stdenv,
# It's necessary to consistently use backendStdenv when building with CUDA support,
# otherwise we get libstdc++ errors downstream.
effectiveStdenv ? if useCuda then cudaPackages.backendStdenv else stdenv,
enableStatic ? effectiveStdenv.hostPlatform.isStatic,
precompileMetalShaders ? false,
useWebUi ? true,
@@ -89,8 +65,7 @@ let
++ lib.optionals useMetalKit [ "MetalKit" ]
++ lib.optionals useMpi [ "MPI" ]
++ lib.optionals useRocm [ "ROCm" ]
++ lib.optionals useVulkan [ "Vulkan" ]
++ lib.optionals useSycl [ "SYCL" ];
++ lib.optionals useVulkan [ "Vulkan" ];
pnameSuffix =
strings.optionalString (suffices != [ ])
@@ -117,7 +92,7 @@ let
cudaBuildInputs = with cudaPackages; [
cuda_cudart
cccl # <nv/target>
cuda_cccl # <nv/target>
libcublas
];
@@ -133,26 +108,6 @@ let
shaderc
spirv-headers
];
syclAot = useSycl && syclDeviceArch != null && syclDeviceArch != "";
# source ocloc binary from intel-compute-runtime
oclocAot = runCommand "ocloc-aot" { nativeBuildInputs = [ makeBinaryWrapper ]; } ''
mkdir -p "$out/bin"
shopt -s nullglob
exact=(${lib.getBin intel-compute-runtime}/bin/ocloc)
vers=(${lib.getBin intel-compute-runtime}/bin/ocloc-*)
if [ ''${#exact[@]} -eq 1 ]; then
src=''${exact[0]}
elif [ ''${#vers[@]} -eq 1 ]; then
src=''${vers[0]}
else
echo "expected one ocloc binary from intel-compute-runtime" >&2
exit 1
fi
makeWrapper "$src" "$out/bin/ocloc" \
--prefix LD_LIBRARY_PATH : ${lib.makeLibraryPath [ intel-graphics-compiler ]}
'';
in
effectiveStdenv.mkDerivation (finalAttrs: {
@@ -178,13 +133,11 @@ effectiveStdenv.mkDerivation (finalAttrs: {
src = lib.cleanSource ../../.;
};
# Builds Llama Chat locally, taking care not to require updating any sha256 hash.
# Builds the webui locally, taking care not to require updating any sha256 hash.
webui = stdenvNoCC.mkDerivation {
pname = "webui";
version = llamaVersion;
# the app compiles Llama UI from its source in ../../lib/ui, so the source is ui/ as a whole
src = lib.cleanSource ../../ui;
sourceRoot = "source/apps/chat";
src = lib.cleanSource ../../tools/ui;
nativeBuildInputs = [
nodejs
@@ -193,7 +146,7 @@ effectiveStdenv.mkDerivation (finalAttrs: {
# no sha256 required when using buildNodeModules
npmDeps = importNpmLock.buildNodeModules {
npmRoot = ../../ui/apps/chat;
npmRoot = ../../tools/ui;
inherit nodejs;
};
@@ -203,8 +156,8 @@ effectiveStdenv.mkDerivation (finalAttrs: {
};
postPatch = lib.optionalString useWebUi ''
cp -r ${finalAttrs.webui} ui/apps/chat/dist
chmod -R u+w ui/apps/chat/dist
cp -r ${finalAttrs.webui} tools/ui/dist
chmod -R u+w tools/ui/dist
'';
# With PR#6015 https://github.com/ggml-org/llama.cpp/pull/6015,
@@ -213,14 +166,7 @@ effectiveStdenv.mkDerivation (finalAttrs: {
# `xcrun` is used find the path of the Metal compiler, which is varible
# and not on $PATH
# see https://github.com/ggml-org/llama.cpp/pull/6118 for discussion
__noChroot = effectiveStdenv.hostPlatform.isDarwin && useMetalKit && precompileMetalShaders;
# Do not fortify under SYCL as it breaks compiled memcpy invocations
# _FORTIFY_SOURCE rewrites memcpy -> __memcpy_chk
hardeningDisable = optionals useSycl [
"fortify"
"fortify3"
];
__noChroot = effectiveStdenv.isDarwin && useMetalKit && precompileMetalShaders;
nativeBuildInputs =
[
@@ -235,67 +181,48 @@ effectiveStdenv.mkDerivation (finalAttrs: {
autoAddDriverRunpath
]
++ optionals (effectiveStdenv.hostPlatform.isGnu && enableStatic) [ glibc.static ]
++ optionals (effectiveStdenv.hostPlatform.isDarwin && useMetalKit && precompileMetalShaders) [ xcrunHost ]
++ optionals useSycl [
autoAddDriverRunpath
makeBinaryWrapper
]
++ optionals syclAot [ oclocAot ];
++ optionals (effectiveStdenv.isDarwin && useMetalKit && precompileMetalShaders) [ xcrunHost ];
buildInputs =
optionals effectiveStdenv.hostPlatform.isDarwin darwinBuildInputs
optionals effectiveStdenv.isDarwin darwinBuildInputs
++ optionals useCuda cudaBuildInputs
++ optionals useMpi [ mpi ]
++ optionals useRocm rocmBuildInputs
++ optionals useBlas [ blas ]
++ optionals useVulkan vulkanBuildInputs
++ optionals useSycl [
level-zero
ocl-icd
intel-graphics-compiler
]
++ [ openssl ];
cmakeFlags = [
(cmakeBool "LLAMA_BUILD_SERVER" true)
(cmakeBool "LLAMA_BUILD_WEBUI" useWebUi)
(cmakeBool "BUILD_SHARED_LIBS" (!enableStatic))
(cmakeBool "CMAKE_SKIP_BUILD_RPATH" true)
(cmakeBool "GGML_NATIVE" false)
(cmakeBool "GGML_BLAS" useBlas)
(cmakeBool "GGML_CUDA" useCuda)
(cmakeBool "GGML_HIP" useRocm)
(cmakeBool "GGML_METAL" useMetalKit)
(cmakeBool "GGML_VULKAN" useVulkan)
(cmakeBool "GGML_STATIC" enableStatic)
(cmakeBool "GGML_RPC" useRpc)
]
++ optionals useCuda [
(
with cudaPackages.flags;
cmakeFeature "CMAKE_CUDA_ARCHITECTURES" (
builtins.concatStringsSep ";" (map dropDot cudaCapabilities)
cmakeFlags =
[
(cmakeBool "LLAMA_BUILD_SERVER" true)
(cmakeBool "LLAMA_BUILD_WEBUI" useWebUi)
(cmakeBool "BUILD_SHARED_LIBS" (!enableStatic))
(cmakeBool "CMAKE_SKIP_BUILD_RPATH" true)
(cmakeBool "GGML_NATIVE" false)
(cmakeBool "GGML_BLAS" useBlas)
(cmakeBool "GGML_CUDA" useCuda)
(cmakeBool "GGML_HIP" useRocm)
(cmakeBool "GGML_METAL" useMetalKit)
(cmakeBool "GGML_VULKAN" useVulkan)
(cmakeBool "GGML_STATIC" enableStatic)
(cmakeBool "GGML_RPC" useRpc)
]
++ optionals useCuda [
(
with cudaPackages.flags;
cmakeFeature "CMAKE_CUDA_ARCHITECTURES" (
builtins.concatStringsSep ";" (map dropDot cudaCapabilities)
)
)
)
]
++ optionals useRocm [
(cmakeFeature "CMAKE_HIP_COMPILER" "${rocmPackages.llvm.clang}/bin/clang")
(cmakeFeature "CMAKE_HIP_ARCHITECTURES" rocmGpuTargets)
]
++ optionals useMetalKit [
(lib.cmakeFeature "CMAKE_C_FLAGS" "-D__ARM_FEATURE_DOTPROD=1")
(cmakeBool "GGML_METAL_EMBED_LIBRARY" (!precompileMetalShaders))
]
++ optionals useSycl [
(cmakeBool "GGML_SYCL" true)
(cmakeBool "GGML_SYCL_F16" syclF16)
]
++ optionals syclAot [
(cmakeFeature "GGML_SYCL_DEVICE_ARCH" syclDeviceArch)
]
++ optionals (syclAot && syclMaxParallelLinkJobs != null) [
(cmakeFeature "GGML_SYCL_MAX_PARALLEL_LINK_JOBS" (toString syclMaxParallelLinkJobs))
];
]
++ optionals useRocm [
(cmakeFeature "CMAKE_HIP_COMPILER" "${rocmPackages.llvm.clang}/bin/clang")
(cmakeFeature "CMAKE_HIP_ARCHITECTURES" rocmGpuTargets)
]
++ optionals useMetalKit [
(lib.cmakeFeature "CMAKE_C_FLAGS" "-D__ARM_FEATURE_DOTPROD=1")
(cmakeBool "GGML_METAL_EMBED_LIBRARY" (!precompileMetalShaders))
];
# Environment variables needed for ROCm
env = optionalAttrs useRocm {
@@ -310,39 +237,15 @@ effectiveStdenv.mkDerivation (finalAttrs: {
cp $src/include/llama.h $out/include/
'';
# Fix SYCL binary calling missing important libraries
# Also use Level Zero + sysman INSTEAD of OpenCL
# due to OpenCL reporting free memory as total memory,
# breaking `-fit` functionality
postFixup = lib.optionalString useSycl ''
driverLibs=${
lib.makeLibraryPath [
intel-graphics-compiler
ocl-icd
]
}
for b in "$out"/bin/*; do
[ -f "$b" ] && [ -x "$b" ] || continue
patchelf --print-interpreter "$b" >/dev/null 2>&1 || continue
patchelf --add-needed libOpenCL.so.1 --add-needed libigc.so.2 \
--add-rpath "$driverLibs" "$b"
wrapProgram "$b" \
--set-default ONEAPI_DEVICE_SELECTOR level_zero:gpu \
--set-default ZES_ENABLE_SYSMAN 1
done
'';
meta = {
# Configurations we don't want even the CI to evaluate. Results in the
# "unsupported platform" messages. This is mostly a no-op, because
# cudaPackages would've refused to evaluate anyway.
badPlatforms =
optionals useCuda lib.platforms.darwin
++ optionals useSycl (lib.subtractLists [ "x86_64-linux" ] lib.platforms.all);
badPlatforms = optionals useCuda lib.platforms.darwin;
# Configurations that are known to result in build failures. Can be
# overridden by importing Nixpkgs with `allowBroken = true`.
broken = (useMetalKit && !effectiveStdenv.hostPlatform.isDarwin);
broken = (useMetalKit && !effectiveStdenv.isDarwin);
description = "Inference of LLaMA model in pure C/C++${descriptionSuffix}";
homepage = "https://github.com/ggml-org/llama.cpp/";
+4
View File
@@ -22,6 +22,10 @@ let
gitpython
tabulate
# for examples/pydantic-models-to-grammar-examples.py
docstring-parser
pydantic
];
llama-python-test-deps = with python3Packages; [
+14 -21
View File
@@ -1,18 +1,18 @@
ARG OPENVINO_VERSION_MAJOR=2026.4.1
ARG OPENVINO_VERSION_FULL=2026.4.1.22982.07f9c262b05
ARG OPENVINO_VERSION_MAJOR=2026.2.1
ARG OPENVINO_VERSION_FULL=2026.2.1.21919.ede283a88e3
ARG UBUNTU_VERSION=24.04
# Intel GPU driver versions. https://github.com/intel/compute-runtime/releases
ARG IGC_VERSION=v2.41.5
ARG IGC_VERSION_FULL=2_2.41.5+22716
ARG COMPUTE_RUNTIME_VERSION=26.35.39758.10
ARG COMPUTE_RUNTIME_VERSION_FULL=26.35.39758.10-0
ARG IGC_VERSION=v2.36.3
ARG IGC_VERSION_FULL=2_2.36.3+21719
ARG COMPUTE_RUNTIME_VERSION=26.22.38646.4
ARG COMPUTE_RUNTIME_VERSION_FULL=26.22.38646.4-0
ARG IGDGMM_VERSION=22.10.0
# Intel NPU driver versions. https://github.com/intel/linux-npu-driver/releases
ARG NPU_DRIVER_VERSION=v1.38.0
ARG NPU_DRIVER_FULL=v1.38.0.20260910-34487311128
ARG LIBZE1_VERSION=1.32.0-1~24.04~ppa1
ARG NPU_DRIVER_VERSION=v1.33.0
ARG NPU_DRIVER_FULL=v1.33.0.20260529-26625960453
ARG LIBZE1_VERSION=1.27.0-1~24.04~ppa2
# Optional proxy build arguments
ARG http_proxy=
@@ -28,15 +28,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
## Build Image
@@ -86,16 +83,13 @@ WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
# Build Stage
RUN bash -c "source ${OpenVINO_DIR}/setupvars.sh && \
cmake -B build/ReleaseOV -G Ninja \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_BUILD_TESTS=OFF \
-DGGML_NATIVE=OFF \
-DGGML_BACKEND_DL=ON \
-DGGML_CPU_ALL_VARIANTS=ON \
-DGGML_OPENVINO=ON && \
cmake --build build/ReleaseOV --parallel "
@@ -176,7 +170,7 @@ RUN --mount=type=cache,target=/var/cache/intel-npu,sharing=locked \
fi; \
DEB=/var/cache/intel-npu/libze1_${LIBZE1_VERSION}_amd64.deb; \
if [ ! -f "$DEB" ]; then \
wget -q -O "$DEB" https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260830T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb; \
wget -q -O "$DEB" https://snapshot.ppa.launchpadcontent.net/kobuk-team/intel-graphics/ubuntu/20260324T100000Z/pool/main/l/level-zero-loader/libze1_${LIBZE1_VERSION}_amd64.deb; \
fi; \
mkdir /tmp/npu/ && cd /tmp/npu/ && tar -xf "$TGZ" && cp "$DEB" .; \
apt-get update; \
@@ -230,7 +224,6 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
+6 -10
View File
@@ -17,15 +17,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
### Build image
@@ -55,7 +52,7 @@ WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
cmake -S . -B build \
@@ -129,7 +126,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -139,9 +136,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
-1
View File
@@ -133,7 +133,6 @@ ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
WORKDIR /llama.cpp/bin
+17 -15
View File
@@ -9,15 +9,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
@@ -34,7 +31,7 @@ WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=ON -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON && \
cmake --build build --config Release -j$(nproc)
@@ -85,14 +82,20 @@ COPY --from=build /app/full /app
WORKDIR /app
ENV PATH="/root/.venv/bin:/root/.local/bin:${PATH}"
# Flag for compatibility with pip
ARG UV_INDEX_STRATEGY="unsafe-best-match"
RUN apt-get update \
&& apt-get install -y \
build-essential \
curl \
git \
python3 \
python3-pip \
python3-wheel \
&& pip install --break-system-packages --upgrade setuptools \
&& pip install --break-system-packages -r requirements.txt \
ca-certificates \
&& curl -LsSf https://astral.sh/uv/install.sh | sh \
&& uv python install 3.13 \
&& uv venv --python 3.13 /root/.venv \
&& uv pip install --python /root/.venv/bin/python -r requirements.txt \
&& apt autoremove -y \
&& apt clean -y \
&& rm -rf /tmp/* /var/tmp/* \
@@ -104,7 +107,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -114,9 +117,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
+6 -10
View File
@@ -9,15 +9,12 @@ FROM docker.io/node:$NODE_VERSION AS web
ARG APP_VERSION
WORKDIR /app/ui/apps/chat
WORKDIR /app/tools/ui
COPY ui/apps/chat/package.json ui/apps/chat/package-lock.json ./
COPY tools/ui/package.json tools/ui/package-lock.json ./
RUN npm ci
COPY ui/apps/chat/ ./
# the app compiles Llama UI from its source next to it
COPY ui/lib/ui/package.json /app/ui/lib/ui/package.json
COPY ui/lib/ui/src/lib/ /app/ui/lib/ui/src/lib/
COPY tools/ui/ ./
RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build
FROM docker.io/ubuntu:$UBUNTU_VERSION AS build
@@ -31,7 +28,7 @@ WORKDIR /app
COPY . .
COPY --from=web /app/ui/apps/chat/dist ui/apps/chat/dist
COPY --from=web /app/tools/ui/dist tools/ui/dist
RUN cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_ZENDNN=ON && \
cmake --build build -j $(nproc)
@@ -100,7 +97,7 @@ ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app/
COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app
WORKDIR /app
@@ -110,9 +107,8 @@ ENTRYPOINT [ "/app/llama-cli" ]
FROM base AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
COPY --from=build /app/full/llama /app/full/llama-server /app/
COPY --from=build /app/full/llama /app/full/llama-server /app
WORKDIR /app
+1 -1
View File
@@ -10,7 +10,7 @@
build*/
ui/apps/chat/node_modules/
tools/ui/node_modules/
models/*
+1 -1
View File
@@ -1,5 +1,5 @@
{
"Exclude": ["^\\.gitmodules$", "stb_image\\.h", "examples/test-cmake/build/", "examples/test-cmake/build-subdir/"],
"Exclude": ["^\\.gitmodules$", "stb_image\\.h"],
"Disable": {
"IndentSize": true
}
+1 -4
View File
@@ -45,10 +45,7 @@ insert_final_newline = unset
trim_trailing_whitespace = unset
insert_final_newline = unset
[vendor/**.patch]
trim_trailing_whitespace = unset
[ui/**]
[tools/ui/**]
indent_style = unset
indent_size = unset
end_of_line = unset
-2
View File
@@ -5,8 +5,6 @@ exclude =
# Do not traverse examples and tools
examples,
tools,
# Do not traverse .venv directories
.venv*,
# Do not include package initializers
__init__.py,
# No need to traverse our git directory
+1 -1
View File
@@ -1,4 +1,4 @@
blank_issues_enabled: false
blank_issues_enabled: true
contact_links:
- name: Got an idea?
url: https://github.com/ggml-org/llama.cpp/discussions/categories/ideas
-95
View File
@@ -1,95 +0,0 @@
name: "ccache-buckets"
description: "Save/restore latest GitHub Actions ccache matching a key prefix to/from HF buckets"
inputs:
key:
description: "Cache key prefix to match and load"
required: true
folder:
description: "Bucket folder containing ccache files"
required: true
evict-old-files:
description: "Corresponds to the ccache --evict-older-than AGE option, where AGE is the number of seconds or days followed by the 's' or 'd' suffix respectively."
default: ''
save:
description: "Save ccache"
required: false
default: false
type: boolean
hf_bucket:
description: 'Hugging Face buckets path'
required: true
runs:
using: "composite"
steps:
- name: Install Hugging Face Hub CLI
shell: bash
run: |
python3 -m venv .venv-hf
.venv-hf/bin/pip install -U huggingface_hub==1.28.0
- name: Restore ccache from buckets
if: ${{ inputs.save != 'true' }}
shell: bash
run: |
set +e -uo pipefail
source .venv-hf/bin/activate
CCACHE_DIR=$(ccache -k cache_dir)
if [[ -d "$CCACHE_DIR" ]]; then
CACHE_PATH=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path) | last | .path // ""')
if [[ -n "$CACHE_PATH" ]]; then
echo "Restoring ccache from '$CACHE_PATH'."
hf buckets cp "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" ccache_bucket.tar.gz
mkdir -p ccache_bucket
if tar -xzf ccache_bucket.tar.gz -C ccache_bucket; then
rm -rf "$CCACHE_DIR"
mv ccache_bucket "$CCACHE_DIR"
ccache -z
fi
rm ccache_bucket.tar.gz
else
echo "No ccache found."
fi
else
echo "'$CCACHE_DIR' not found."
fi
- name: Save ccache to buckets
if: ${{ inputs.save == 'true' }}
shell: bash
run: |
if [[ -n "$HF_TOKEN" ]]; then
set +e -uo pipefail
source .venv-hf/bin/activate
CCACHE_DIR=$(ccache -k cache_dir)
if [[ -d "$CCACHE_DIR" ]]; then
ccache -s
if [[ -n "${{ inputs.evict-old-files }}" ]]; then
ccache --evict-older-than "${{ inputs.evict-old-files }}"
fi
DATESTAMP=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
CACHEFILE="${{ inputs.key }}-$DATESTAMP.tar.gz"
if tar -czf ccache_bucket.tar.gz -C "$CCACHE_DIR" .; then
hf buckets cp ccache_bucket.tar.gz "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}/$CACHEFILE"
fi
rm ccache_bucket.tar.gz
else
echo "'$CCACHE_DIR' not found."
fi
fi
- name: Remove old ccache files from buckets
if: ${{ inputs.save == 'true' }}
shell: bash
run: |
if [[ -n "$HF_TOKEN" ]]; then
set +e -uo pipefail
source .venv-hf/bin/activate
CACHE_FILES=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select((.uploaded_at | .[:19]+"Z" | fromdateiso8601) < (now - 5 * 60)) | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path)[:-1] | .[] | [.path // ""] | @tsv')
if [[ -n "$CACHE_FILES" ]]; then
echo "Removing old ccache files..."
while IFS=$'\t' read -r CACHE_PATH; do
hf buckets rm "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" -y
done <<< "$CACHE_FILES"
fi
fi
+10 -38
View File
@@ -1,50 +1,22 @@
# note: place this as the last step of the job, so the new cache is saved by "Post ccache" right after the old one is cleared
name: "ccache-clear"
description: "Delete GitHub Actions caches matching a key prefix, oldest first"
description: "Delete all GitHub Actions caches matching a key prefix"
inputs:
key:
description: "Cache key prefix to match and delete"
required: true
older:
description: "Only delete caches created more than this long ago (e.g. 90m, 1h, 1d). By default all matching caches are deleted"
required: false
default: ""
min:
description: "Stop deleting if fewer than this many caches would remain (e.g. 1). By default there is no minimum"
required: false
default: "0"
dry-run:
description: "Only print the caches that would be deleted, without deleting them"
required: false
default: "false"
runs:
using: "composite"
steps:
- name: Install GitHub CLI if missing
shell: bash
run: |
# e.g. in container jobs, where it is not preinstalled
if ! command -v gh >/dev/null 2>&1; then
echo "GitHub CLI not found, installing..."
if ! command -v curl >/dev/null 2>&1; then
apt-get update >/dev/null 2>&1 || true
apt-get install -y curl >/dev/null 2>&1 || true
fi
mkdir -p -m 755 /etc/apt/keyrings
curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | tee /etc/apt/keyrings/githubcli-archive-keyring.gpg >/dev/null
chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" > /etc/apt/sources.list.d/github-cli.list
apt-get update >/dev/null 2>&1 || true
apt-get install -y gh || { echo "Failed to install GitHub CLI (gh)" >&2; exit 1; }
fi
command -v gh >/dev/null 2>&1 || { echo "GitHub CLI (gh) is required but could not be installed" >&2; exit 1; }
- name: Clear caches
shell: bash
run: |
bash scripts/ccache-clear.sh \
--key "${{ inputs.key }}" \
--older "${{ inputs.older }}" \
--min "${{ inputs.min }}" \
${{ inputs.dry-run == 'true' && '--dry-run' || '' }}
CACHES=$(gh cache list --key "ccache-${{ inputs.key }}" --json id,key --jq '.[] | "\(.id) \(.key)"' 2>/dev/null)
if [ -z "$CACHES" ]; then
echo "No caches found with key prefix: ${{ inputs.key }}"
exit 0
fi
while read -r id key; do
echo "Deleting cache: $id ($key)"
gh cache delete "$id"
done <<< "$CACHES"
+1 -3
View File
@@ -14,9 +14,7 @@ runs:
run: |
BUILD_NUMBER="$(git rev-list --count HEAD)"
SHORT_HASH="$(git rev-parse --short=7 HEAD)"
if [[ "$GITHUB_REF_TYPE" == "tag" && "${{ env.BRANCH_NAME }}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
echo "name=${{ env.BRANCH_NAME }}" >> $GITHUB_OUTPUT
elif [[ "${{ env.BRANCH_NAME }}" == "master" || "${{ env.BRANCH_NAME }}" == "b${BUILD_NUMBER}" ]]; then
if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
else
SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
@@ -0,0 +1,20 @@
name: "Linux - Setup Vulkan SDK"
description: "Setup Vulkan SDK for Linux"
inputs:
path:
description: "Installation path"
required: true
version:
description: "Vulkan SDK version"
required: true
runs:
using: "composite"
steps:
- name: Setup Vulkan SDK
id: setup
uses: ./.github/actions/unarchive-tar
with:
url: https://sdk.lunarg.com/sdk/download/${{ inputs.version }}/linux/vulkan_sdk.tar.xz
path: ${{ inputs.path }}
strip: 1
+48 -47
View File
@@ -6,7 +6,8 @@ inputs:
required: true
cuda_arch:
description: "CUDA target architecture"
required: true
required: false
default: "x64"
runs:
using: "composite"
@@ -100,56 +101,56 @@ runs:
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_1=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.1" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
- name: Install Cuda Toolkit 13.5 for x64
if: ${{ inputs.cuda_version == '13.5' && inputs.cuda_arch == 'x64' }}
- name: Install Cuda Toolkit 13.3
if: ${{ inputs.cuda_version == '13.3' }}
shell: pwsh
run: |
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5"
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3"
choco install unzip -y
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-13.10.0.20-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-13.5.25-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-13.5.25-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-13.5.25-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cccl/windows-x86_64/cccl-windows-x86_64-13.3.5.0.6-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_crt-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_cudart-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_nvcc-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_nvrtc-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\libcublas-windows-x86_64-13.10.0.20-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\libnvvm-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_nvtx-windows-x86_64-13.5.25-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_profiler_api-windows-x86_64-13.5.25-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\visual_studio_integration-windows-x86_64-13.5.25-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cccl-windows-x86_64-13.3.5.0.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_5=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-x86_64/cuda_cudart-windows-x86_64-13.3.29-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvrtc/windows-x86_64/cuda_nvrtc-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-x86_64/libcublas-windows-x86_64-13.5.1.27-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.3.33-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvtx/windows-x86_64/cuda_nvtx-windows-x86_64-13.3.29-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_profiler_api/windows-x86_64/cuda_profiler_api-windows-x86_64-13.3.27-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/visual_studio_integration/windows-x86_64/visual_studio_integration-windows-x86_64-13.3.27-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cccl/windows-x86_64/cccl-windows-x86_64-13.3.3.3.1-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_crt-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_cudart-windows-x86_64-13.3.29-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvcc-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvrtc-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\libcublas-windows-x86_64-13.5.1.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\libnvvm-windows-x86_64-13.3.33-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_nvtx-windows-x86_64-13.3.29-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cuda_profiler_api-windows-x86_64-13.3.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\visual_studio_integration-windows-x86_64-13.3.27-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\cccl-windows-x86_64-13.3.3.3.1-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_3=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.3" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
- name: Install Cuda Toolkit 13.5 for ARM64
if: ${{ inputs.cuda_version == '13.5' && inputs.cuda_arch == 'arm64' }}
- name: Install Cuda Toolkit 13.4 for ARM64
if: ${{ inputs.cuda_version == '13.4' && inputs.cuda_arch == 'arm64' }}
shell: pwsh
run: |
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5"
mkdir -p "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4"
choco install unzip -y
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cccl/windows-x86_64/cccl-windows-x86_64-13.3.5.0.6-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_crt/windows-x86_64/cuda_crt-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_nvcc/windows-x86_64/cuda_nvcc-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libnvvm/windows-x86_64/libnvvm-windows-x86_64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/cuda_cudart/windows-arm64/cuda_cudart-windows-arm64-13.5.37-archive.zip"
curl -O "https://developer.download.nvidia.com/compute/cuda/redist/libcublas/windows-arm64/libcublas-windows-arm64-13.10.0.20-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cccl-windows-x86_64-13.3.5.0.6-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_crt-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_nvcc-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\libnvvm-windows-x86_64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\cuda_cudart-windows-arm64-13.5.37-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\libcublas-windows-arm64-13.10.0.20-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_5=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.5" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
curl -O "https://packages.nvidia.com/bin-archive/pool/windows-x86_64/5B515474-7E78-11F1-8656-C51E4F4B317F/cccl-windows-x86_64-13.3.4.1.2-archive.zip"
curl -O "https://packages.nvidia.com/bin-archive/pool/windows-x86_64/5B515474-7E78-11F1-8656-C51E4F4B317F/cuda_crt-windows-x86_64-13.4.46-archive.zip"
curl -O "https://packages.nvidia.com/bin-archive/pool/windows-x86_64/5B515474-7E78-11F1-8656-C51E4F4B317F/cuda_nvcc-windows-x86_64-13.4.46-archive.zip"
curl -O "https://packages.nvidia.com/bin-archive/pool/windows-x86_64/5B515474-7E78-11F1-8656-C51E4F4B317F/libnvvm-windows-x86_64-13.4.46-archive.zip"
curl -O "https://packages.nvidia.com/bin-archive/pool/windows-arm64/5B515474-7E78-11F1-8656-C51E4F4B317F/cuda_cudart-windows-arm64-13.4.46-archive.zip"
curl -O "https://packages.nvidia.com/bin-archive/pool/windows-arm64/5B515474-7E78-11F1-8656-C51E4F4B317F/libcublas-windows-arm64-13.7.0.10-archive.zip"
unzip '*.zip' -d "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4"
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cccl-windows-x86_64-13.3.4.1.2-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_crt-windows-x86_64-13.4.46-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_nvcc-windows-x86_64-13.4.46-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\libnvvm-windows-x86_64-13.4.46-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\cuda_cudart-windows-arm64-13.4.46-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
xcopy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\libcublas-windows-arm64-13.7.0.10-archive\*" "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" /E /I /H /Y
echo "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
echo "CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
echo "CUDA_PATH_V13_4=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v13.4" | Out-File -FilePath $env:GITHUB_ENV -Append -Encoding utf8
@@ -24,7 +24,7 @@ runs:
write-host "Installing ROCm wheels for multi-arch support"
# Install ROCm wheels for multi-arch support (this may take several minutes)
python -m pip install --index-url https://stable.repo.amd.com/rocm/whl-next/ "rocm[libraries,devel]==${{ inputs.version }}"
python -m pip install --index-url https://repo.amd.com/rocm/whl-multi-arch/ "rocm[libraries,devel]==${{ inputs.version }}"
# Pre-expand the devel tree so it is included in the cache
write-host "Initializing ROCm devel tree"
+2 -1
View File
@@ -48,6 +48,7 @@ examples:
- all-globs-to-all-files:
- '!tools/server/**'
- '!tools/mtmd/**'
- '!tools/ui/**'
testing:
- changed-files:
- any-glob-to-any-file:
@@ -71,7 +72,7 @@ android:
server/ui:
- changed-files:
- any-glob-to-any-file:
- ui/**
- tools/ui/**
server:
- changed-files:
- any-glob-to-any-file:
-4
View File
@@ -4,10 +4,6 @@ on:
issues:
types: [opened]
cache-mode: none
permissions:
contents: read
jobs:
find-related:
if: github.event.action == 'opened'
-172
View File
@@ -1,172 +0,0 @@
name: Behavior Check
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/behavior-check.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.py',
'**/requirements*.txt',
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/behavior-check.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.py',
'**/requirements*.txt',
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
GGML_SCHED_DEBUG_REALLOC: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu:
runs-on: ubuntu-26.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: Build Dependencies
id: build_depends
run: |
sudo apt update
sudo apt install -y build-essential libssl-dev git-lfs libjpeg-dev python3 python3-venv python3-pip
- name: Python Dependencies
id: python_depends
run: |
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements/requirements-convert_hf_to_gguf.txt
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: behavior-check-ubuntu-26.04-arm
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
cmake -B build \
-DGGML_NATIVE=OFF \
-DGGML_BACKEND_DL=OFF \
-DLLAMA_FATAL_WARNINGS=ON
time cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: behavior-check-ubuntu-26.04-arm
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Test
id: cmake_test
run: |
source .venv/bin/activate
cd build
ctest -L behavior -LE 'model|backend' --verbose --timeout 900
windows:
runs-on: windows-2025
cache-mode: write
permissions:
actions: write
contents: read
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
key: behavior-check-windows-2025
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Python Dependencies
id: python_depends
shell: bash
run: |
python3 -m venv .venv
source .venv/Scripts/activate
pip install -r requirements/requirements-convert_hf_to_gguf.txt
- name: Build
id: cmake_build
shell: cmd
run: |
call "C:\Program Files\Microsoft Visual Studio\18\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
cmake -B build -G "Ninja Multi-Config" ^
-DCMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake ^
-DCMAKE_BUILD_TYPE=Release ^
-DGGML_NATIVE=OFF ^
-DGGML_BACKEND_DL=OFF
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS%
- name: Test
id: cmake_test
shell: bash
run: |
source .venv/Scripts/activate
cd build
ctest -C Release -L behavior -LE 'model|backend' --verbose --timeout 900
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: behavior-check-windows-2025
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
+2 -6
View File
@@ -15,10 +15,6 @@ on:
'**/*.cpp'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -31,8 +27,8 @@ env:
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-26-llguidance:
runs-on: ${{ 'ubuntu-26.04-arm' || 'ubuntu-26.04' }}
ubuntu-24-llguidance:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
steps:
- name: Clone
@@ -23,27 +23,19 @@ on:
- 'scripts/snapdragon/**'
- 'CMakePresets.json'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
android-ndk-snapdragon:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.8'
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.7'
defaults:
run:
shell: bash
permissions:
actions: write
contents: read
steps:
- name: Clone
uses: actions/checkout@v6
@@ -67,17 +59,13 @@ jobs:
path: pkg-snapdragon/llama.cpp
linux-iot-snapdragon:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-linux:v0.8'
image: 'ghcr.io/snapdragon-toolchain/arm64-linux:v0.7'
defaults:
run:
shell: bash
permissions:
actions: write
contents: read
steps:
- name: Clone
uses: actions/checkout@v6
@@ -103,16 +91,12 @@ jobs:
test-snapdragon-qdc:
name: Test on QDC Device (${{ matrix.device }})
needs: [android-ndk-snapdragon, linux-iot-snapdragon]
runs-on: ubuntu-26.04-arm
timeout-minutes: 180
runs-on: ubuntu-24.04-arm
timeout-minutes: 90
strategy:
fail-fast: false
matrix:
device: [SM8850, QCS9075M]
permissions:
actions: read
contents: read
device: [SM8750, SM8850, QCS9075M]
steps:
- name: Checkout
@@ -155,7 +139,7 @@ jobs:
--pkg-dir pkg-snapdragon/llama.cpp \
--model-url "https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_0.gguf" \
--device ${{ matrix.device }} \
${{ startsWith(matrix.device, 'QCS') && '--job-timeout 5400 --retries 2 --retry-delay 300' || '' }}
${{ startsWith(matrix.device, 'QCS') && '--retries 2 --retry-delay 300' || '' }}
env:
QDC_API_KEY: ${{ secrets.QDC_API_KEY }}
+6 -15
View File
@@ -20,10 +20,6 @@ on:
- '.github/workflows/build-android.yml'
- 'examples/llama.android/**'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -37,7 +33,7 @@ env:
jobs:
default:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- name: Clone
@@ -53,10 +49,9 @@ jobs:
distribution: zulu
- name: Setup Android SDK
uses: android-actions/setup-android@be39fa834029ff78f1a44aa3bb0819b8fc2bd8fd # v4.0.4
uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
with:
log-accepted-android-sdk-licenses: false
packages: platform-tools cmake;3.31.6
- name: Build
run: |
@@ -64,17 +59,13 @@ jobs:
./gradlew build --no-daemon
ndk:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
container:
image: 'ghcr.io/snapdragon-toolchain/arm64-android:v0.3'
defaults:
run:
shell: bash
permissions:
actions: write
contents: read
steps:
- name: Clone
uses: actions/checkout@v6
@@ -102,7 +93,7 @@ jobs:
path: pkg-adb/llama.cpp
arm64:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
env:
NDK_VERSION: "29.0.14206865"
@@ -119,7 +110,7 @@ jobs:
# cache on: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78224189394
#
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.24
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: android-ubuntu-arm64
# evict-old-files: 1d
@@ -132,7 +123,7 @@ jobs:
distribution: temurin
- name: Setup Android SDK
uses: android-actions/setup-android@be39fa834029ff78f1a44aa3bb0819b8fc2bd8fd # v4.0.4
uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
with:
log-accepted-android-sdk-licenses: false
-160
View File
@@ -1,160 +0,0 @@
name: CI (apple - daily)
on:
workflow_dispatch: # allows manual triggering
schedule:
- cron: '0 0 * * *'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
macos-latest-ios-xcode:
runs-on: macos-latest
permissions:
actions: write
contents: read
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Xcode
uses: ggml-org/setup-xcode@v1
with:
xcode-version: latest-stable
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=iOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
- name: xcodebuild for swift package
id: xcodebuild
run: |
./build-xcframework.sh
- name: Upload xcframework artifact
uses: actions/upload-artifact@v6
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
retention-days: 1
- name: Build Xcode project
run: |
xcodebuild -downloadPlatform iOS
xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
macos-latest-tvos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=tvOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-visionos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=visionOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-swift:
runs-on: macos-latest
needs: macos-latest-ios-xcode
permissions:
actions: read
contents: read
strategy:
matrix:
destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Download xcframework artifact
uses: actions/download-artifact@v7
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
- name: Build llama.cpp with CMake
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
+195 -40
View File
@@ -22,14 +22,9 @@ on:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-apple.yml',
'ggml/src/ggml-metal/**',
'ggml/src/ggml-rpc/**'
'ggml/src/ggml-metal/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -37,7 +32,6 @@ concurrency:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
GGML_SCHED_DEBUG_REALLOC: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
@@ -52,19 +46,11 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-arm64
folder: llama.cpp
hf_bucket: ggml-org/cache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
@@ -79,31 +65,200 @@ jobs:
-DGGML_RPC=ON \
-DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: apple-arm64
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Check for leaks
run: |
cmd=(./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1)
leaks -atExit -- "${cmd[@]}"
# Graphics devices are leaked by Metal in Apple code sometimes, so we ignore those leaks
OBJC_DEBUG_MISSING_POOLS=YES "${cmd[@]}" 2>&1 | awk '{ print } index($0, "autoreleased with no pool in place") && !/class [a-zA-Z0-9]+Device autoreleased/ { found = 1 } END { exit found }'
leaks -atExit -- ./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1
- name: Test
id: cmake_test
run: |
cd build
# Metal Paravirtual devices are difficult to support -> disable
# ref: https://github.com/ggml-org/llama.cpp/pull/19802#issuecomment-4013704023
ctest -L main -E "test-llama-archs|test-llama-context|test-speculative-rejection-sampling" --verbose --timeout 900
ctest -L main -E "test-llama-archs" --verbose --timeout 900
macos-latest-x64:
runs-on: macos-15-intel
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-x64
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
# Metal is disabled due to intermittent failures with Github runners not having a GPU:
# https://github.com/ggml-org/llama.cpp/actions/runs/8635935781/job/23674807267#step:5:2313
cmake -B build \
-DCMAKE_BUILD_RPATH="@loader_path" \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_BUILD_BORINGSSL=ON \
-DGGML_METAL=OFF \
-DGGML_RPC=ON \
-DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
macos-latest-ios-xcode:
runs-on: macos-latest
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Xcode
uses: ggml-org/setup-xcode@v1
with:
xcode-version: latest-stable
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=iOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
- name: xcodebuild for swift package
id: xcodebuild
run: |
./build-xcframework.sh
- name: Upload xcframework artifact
uses: actions/upload-artifact@v6
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
retention-days: 1
- name: Build Xcode project
run: |
xcodebuild -downloadPlatform iOS
xcodebuild -project examples/llama.swiftui/llama.swiftui.xcodeproj -scheme llama.swiftui -sdk iphoneos CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY= -destination 'generic/platform=iOS' FRAMEWORK_FOLDER_PATH=./build-ios build
macos-latest-tvos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# TODO: this likely does not do anything - if yes, remove it
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-tvos
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=tvOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-visionos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# TODO: this likely does not do anything - if yes, remove it
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-visionos
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_BUILD_COMMON=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_SYSTEM_NAME=visionOS \
-DCMAKE_OSX_DEPLOYMENT_TARGET=1.0 \
-DCMAKE_XCODE_ATTRIBUTE_DEVELOPMENT_TEAM=ggml
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) -- CODE_SIGNING_ALLOWED=NO
macos-latest-swift:
runs-on: macos-latest
needs: macos-latest-ios-xcode
strategy:
matrix:
destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# TODO: this likely does not do anything - if yes, remove it
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: apple-swift
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Download xcframework artifact
uses: actions/download-artifact@v7
with:
name: llama-xcframework
path: build-apple/llama.xcframework/
- name: Build llama.cpp with CMake
id: cmake_build
run: |
sysctl -a
cmake -B build -G Xcode \
-DGGML_METAL_EMBED_LIBRARY=ON \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_SERVER=OFF \
-DCMAKE_OSX_ARCHITECTURES="arm64;x86_64"
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
+35 -12
View File
@@ -5,15 +5,38 @@ on:
schedule:
- cron: '0 * * * *'
cache-mode: write
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
ubuntu-24-vulkan-cache:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Get latest Vulkan SDK version
id: vulkan_sdk_version
run: |
echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
- name: Setup Cache
uses: actions/cache@v5
id: cache-sdk
with:
path: ./vulkan_sdk
key: cache-gha-vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
- name: Setup Vulkan SDK
if: steps.cache-sdk.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-vulkan
with:
path: ./vulkan_sdk
version: ${{ env.VULKAN_SDK_VERSION }}
#ubuntu-24-spacemit-cache:
# runs-on: ubuntu-24.04
@@ -40,13 +63,13 @@ jobs:
# path: ./spacemit_toolchain
# version: ${{ env.SPACEMIT_IME_TOOLCHAIN_VERSION }}
ubuntu-26-openvino-cache:
runs-on: ubuntu-26.04
ubuntu-24-openvino-cache:
runs-on: ubuntu-24.04
env:
# Sync versions in build-openvino.yml, ci-self-hosted-openvino.yml, release.yml, release-publish.yml, build-cache.yml, .devops/openvino.Dockerfile, docs/backend/OPENVINO.md
OPENVINO_VERSION_MAJOR: "2026.4.1"
OPENVINO_VERSION_FULL: "2026.4.1.22982.07f9c262b05"
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
@@ -72,9 +95,9 @@ jobs:
runs-on: windows-2022
env:
# Sync versions in build-openvino.yml, ci-self-hosted-openvino.yml, release.yml, release-publish.yml, build-cache.yml, .devops/openvino.Dockerfile, docs/backend/OPENVINO.md
OPENVINO_VERSION_MAJOR: "2026.4.1"
OPENVINO_VERSION_FULL: "2026.4.1.22982.07f9c262b05"
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
-4
View File
@@ -22,10 +22,6 @@ on:
'ggml/src/ggml-cann/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
+57
View File
@@ -0,0 +1,57 @@
name: Build relocatable cmake package
on:
workflow_dispatch:
workflow_call:
jobs:
linux:
runs-on: [self-hosted, Linux]
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Build
run: |
PREFIX="$(pwd)"/inst
cmake -S . -B build \
-DCMAKE_PREFIX_PATH="$PREFIX" \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_IS_DEV=OFF \
-DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j $(nproc)
cmake --install build --prefix "$PREFIX" --config Release
export LLAMA_CONFIG="$PREFIX"/lib/cmake/llama/llama-config.cmake
tclsh <<'EOF'
set build(commit) [string trim [exec git rev-parse --short HEAD]]
set build(number) [string trim [exec git rev-list --count HEAD]]
set cmakelists [read [open "CMakeLists.txt" r]]
regexp {set\(LLAMA_VERSION_MAJOR\s+(\d+)\)} $cmakelists -> major
regexp {set\(LLAMA_VERSION_MINOR\s+(\d+)\)} $cmakelists -> minor
regexp {set\(LLAMA_VERSION_PATCH\s+(\d+)\)} $cmakelists -> patch
set build(version) "$major.$minor.$patch"
set llamaconfig [read [open "$env(LLAMA_CONFIG)" r]]
set checks [list "set\\(LLAMA_VERSION \\s+$build(version)\\)" \
"set\\(LLAMA_BUILD_COMMIT\\s+$build(commit)\\)" \
"set\\(LLAMA_BUILD_NUMBER\\s+$build(number)\\)"]
puts -nonewline "Checking llama-config.cmake version... "
foreach check $checks {
if {![regexp -expanded -- $check $llamaconfig]} {
puts "\"$check\" failed!"
exit 1
}
}
puts "success."
EOF
cd examples/simple-cmake-pkg
cmake -S . -B build -DCMAKE_PREFIX_PATH="$PREFIX"/lib/cmake
cmake --build build -j $(nproc)
+38 -129
View File
@@ -7,6 +7,7 @@ on:
- master
paths: [
'.github/workflows/build-cpu.yml',
'.github/workflows/build-cmake-pkg.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
@@ -19,7 +20,7 @@ on:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-cpu.yml',
'ggml/src/ggml-rpc/**',
'.github/workflows/build-cmake-pkg.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
@@ -28,10 +29,6 @@ on:
'**/*.cpp'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -39,20 +36,22 @@ concurrency:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
GGML_SCHED_DEBUG_REALLOC: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
build-cmake-pkg:
uses: ./.github/workflows/build-cmake-pkg.yml
ubuntu:
strategy:
matrix:
include:
- build: 'x64'
os: ubuntu-26.04
os: ubuntu-22.04
- build: 'arm64'
os: ubuntu-26.04-arm
os: ubuntu-24.04-arm
runs-on: ${{ matrix.os }}
@@ -62,10 +61,11 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
save: false
key: cpu-${{ matrix.os }}
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build Dependencies
id: build_depends
@@ -76,21 +76,19 @@ jobs:
libjpeg-dev build-essential libssl-dev \
git-lfs
- name: Toolchain workaround (GCC 14)
if: ${{ contains(matrix.os, 'ubuntu-24.04') }}
run: |
sudo apt-get install -y gcc-14 g++-14
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Python Dependencies
id: python_depends
run: |
export PIP_BREAK_SYSTEM_PACKAGES="1"
python3 -m pip install --upgrade pip setuptools
pip3 install ./gguf-py jinja2==3.1.6
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: cpu-${{ matrix.os }}
folder: llama.cpp
hf_bucket: ggml-org/cache
pip3 install ./gguf-py
- name: Build
id: cmake_build
@@ -98,21 +96,10 @@ jobs:
cmake -B build \
-DGGML_NATIVE=OFF \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_RPC=ON
-DGGML_RPC=ON \
-DGGML_NATIVE=OFF
time cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: cpu-${{ matrix.os }}
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Test
id: cmake_test
run: |
@@ -131,30 +118,28 @@ jobs:
./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
windows:
name: windows / ${{ matrix.build }}
runs-on: windows-2025
cache-mode: write
permissions:
actions: write
contents: read
env:
OPENBLAS_VERSION: 0.3.23
SDE_VERSION: 9.33.0-2024-01-07
VULKAN_VERSION: 1.4.357.0
strategy:
matrix:
include:
- build: 'x64-cpu-static'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_OPENMP_FETCH=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DBUILD_SHARED_LIBS=OFF'
- build: 'x64-openblas'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_OPENMP=OFF -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
- build: 'x64-vulkan'
arch: 'x64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DGGML_VULKAN=ON'
- build: 'arm64'
arch: 'arm64'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DGGML_OPENMP_FETCH=ON -DLLAMA_BUILD_SERVER=ON'
defines: '-G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DGGML_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON'
steps:
- name: Clone
@@ -162,7 +147,7 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
key: cpu-windows-2025-${{ matrix.build }}
variant: ccache
@@ -182,6 +167,15 @@ jobs:
$lib = $(join-path $msvc 'bin\Hostx64\x64\lib.exe')
& $lib /machine:x64 "/def:${env:RUNNER_TEMP}/openblas/lib/libopenblas.def" "/out:${env:RUNNER_TEMP}/openblas/lib/openblas.lib" /name:openblas.dll
- name: Install Vulkan SDK
id: get_vulkan
if: ${{ matrix.build == 'x64-vulkan' }}
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
- name: Install Ninja
id: install_ninja
run: |
@@ -219,90 +213,5 @@ jobs:
# 7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar
# $sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe)
# cd build
# $env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
# & $sde -future -- ctest -L main -C Release --verbose --timeout 900
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: cpu-windows-2025-${{ matrix.build }}
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
build-cmake-pkg:
runs-on: ubuntu-24.04
steps:
- name: Clone
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: build-cmake-pkg
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
run: |
PREFIX="$(pwd)"/inst
cmake -S . -B build \
-DCMAKE_PREFIX_PATH="$PREFIX" \
-DLLAMA_OPENSSL=OFF \
-DLLAMA_BUILD_TESTS=OFF \
-DLLAMA_BUILD_TOOLS=OFF \
-DLLAMA_BUILD_EXAMPLES=OFF \
-DLLAMA_BUILD_APP=OFF \
-DLLAMA_BUILD_IS_DEV=OFF \
-DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j $(nproc)
cmake --install build --prefix "$PREFIX" --config Release
export LLAMA_CONFIG="$PREFIX"/lib/cmake/llama/llama-config.cmake
build_commit=$(git rev-parse --short HEAD | xargs)
build_number=$(git rev-list --count HEAD | xargs)
major=$(grep -oE "set\(LLAMA_VERSION_MAJOR[[:space:]]+[0-9]+" CMakeLists.txt | grep -oE "[0-9]+$")
minor=$(grep -oE "set\(LLAMA_VERSION_MINOR[[:space:]]+[0-9]+" CMakeLists.txt | grep -oE "[0-9]+$")
patch=$(grep -oE "set\(LLAMA_VERSION_PATCH[[:space:]]+[0-9]+" CMakeLists.txt | grep -oE "[0-9]+$")
build_version="$major.$minor.$patch"
checks=("set\(LLAMA_VERSION[[:space:]]+$build_version\)"
"set\(LLAMA_BUILD_COMMIT[[:space:]]+$build_commit\)"
"set\(LLAMA_BUILD_NUMBER[[:space:]]+$build_number\)")
for check in "${checks[@]}"; do
if ! grep -qE "$check" "$LLAMA_CONFIG"; then
echo "Checking llama-config.cmake version... \"$check\" failed!"
exit 1
fi
done
echo "Checking llama-config.cmake version... success."
cd examples/simple-cmake-pkg
cmake -S . -B build -DCMAKE_PREFIX_PATH="$PREFIX"/lib/cmake
cmake --build build -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: build-cmake-pkg
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
+4 -8
View File
@@ -15,10 +15,6 @@ on:
schedule:
- cron: '0 0 * * 0'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -163,7 +159,7 @@ jobs:
# cmake --build build --config Release -j $(nproc)
debian-13-loongarch64-cpu-cross:
runs-on: ${{ 'ubuntu-26.04-arm' || 'ubuntu-26.04' }}
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
container: debian@sha256:653dfb9f86c3782e8369d5f7d29bb8faba1f4bff9025db46e807fa4c22903671
steps:
@@ -218,7 +214,7 @@ jobs:
cmake --build build --config Release -j $(nproc)
debian-13-loongarch64-vulkan-cross:
runs-on: ${{ 'ubuntu-26.04-arm' || 'ubuntu-26.04' }}
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
container: debian@sha256:653dfb9f86c3782e8369d5f7d29bb8faba1f4bff9025db46e807fa4c22903671
steps:
@@ -276,8 +272,8 @@ jobs:
cmake --build build --config Release -j $(nproc)
ubuntu-26-riscv64-cpu-spacemit-ime-cross:
runs-on: ubuntu-26.04
ubuntu-24-riscv64-cpu-spacemit-ime-cross:
runs-on: ubuntu-24.04
env:
# Make sure this is in sync with build-cache.yml
+18 -83
View File
@@ -24,10 +24,6 @@ on:
'ggml/src/ggml-cuda/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -54,25 +50,17 @@ jobs:
DEBIAN_FRONTEND: noninteractive
run: |
apt update
apt install -y cmake build-essential ninja-build libgomp1 git libssl-dev jq python3 python3-venv python3-pip
apt install -y cmake build-essential ninja-build libgomp1 git libssl-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: cuda-ubuntu-24.04-cuda
folder: llama.cpp
hf_bucket: ggml-org/cache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with CMake
# TODO: Drop GGML_CUDA_CCCL_VERSION when this job uses CTK >= 13.5, which bundles CCCL >= 3.5.
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
run: |
cmake -S . -B build -G Ninja \
-DLLAMA_FATAL_WARNINGS=ON \
@@ -81,24 +69,12 @@ jobs:
-DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
-DGGML_NATIVE=OFF \
-DGGML_CUDA=ON \
-DGGML_CUDA_CCCL_VERSION=v3.4.3
-DGGML_CUDA_CUB_3DOT2=ON
cmake --build build
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: cuda-ubuntu-24.04-cuda
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
hip:
runs-on: ubuntu-22.04
container: rocm/dev-ubuntu-22.04:6.3.4
container: rocm/dev-ubuntu-22.04:6.1.2
steps:
- name: Clone
@@ -109,22 +85,14 @@ jobs:
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev jq python3-venv
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev rocwmma-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: cuda-ubuntu-22.04-hip
folder: llama.cpp
hf_bucket: ggml-org/cache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with native CMake HIP support
id: cmake_build
@@ -135,21 +103,9 @@ jobs:
-DGGML_HIP=ON
cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: cuda-ubuntu-22.04-hip
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
musa:
runs-on: ubuntu-22.04
container: registry.mthreads.com/mcconline/musa_sdk:5.2.0-devel-ubuntu22.04-s5000
container: mthreads/musa:rc4.3.0-devel-ubuntu22.04-amd64
steps:
- name: Clone
@@ -160,39 +116,18 @@ jobs:
id: depends
run: |
apt-get update
apt-get install -y build-essential git cmake libssl-dev jq python3-venv musa-mualg-5-2 musa-muthrust-5-2 libmthreads-compute
apt-get install -y build-essential git cmake libssl-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: cuda-ubuntu-22.04-musa
folder: llama.cpp
hf_bucket: ggml-org/cache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with native CMake MUSA support
id: cmake_build
run: |
cmake -B build -S . \
-DGGML_MUSA=ON \
-DMUSA_ARCHITECTURES=31
cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: cuda-ubuntu-22.04-musa
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
-DGGML_MUSA=ON
time cmake --build build --config Release -j $(nproc)
+15 -27
View File
@@ -7,11 +7,6 @@ name: CI (CUDA, windows)
on:
workflow_dispatch: # allows manual triggering
cache-mode: write
permissions:
actions: write
contents: read
# note: this will run in queue with the release workflow
concurrency:
group: release
@@ -27,7 +22,6 @@ env:
jobs:
cuda:
name: windows-cuda (${{ matrix.cuda }}, ${{ matrix.arch }})
runs-on: windows-2022
permissions:
@@ -35,17 +29,7 @@ jobs:
strategy:
matrix:
include:
# CTK >= 13.5 bundles CCCL >= 3.5; omit GGML_CUDA_CCCL_VERSION for those versions.
- cuda: '12.4'
arch: x64
defines: '-DGGML_CUDA_CCCL_VERSION=v3.4.3'
- cuda: '13.5'
arch: x64
defines: ''
- cuda: '13.5'
arch: arm64
defines: '-DCMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-msvc-cuda.cmake'
cuda: ['12.4', '13.3']
steps:
- name: Clone
@@ -53,15 +37,14 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
key: release-windows-2022-${{ matrix.arch }}-cuda-${{ matrix.cuda }}
key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
- name: Install Cuda Toolkit
uses: ./.github/actions/windows-setup-cuda
with:
cuda_version: ${{ matrix.cuda }}
cuda_arch: ${{ matrix.arch }}
- name: Install Ninja
id: install_ninja
@@ -71,21 +54,26 @@ jobs:
- name: Build
id: cmake_build
shell: cmd
# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
run: |
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" ${{ matrix.arch == 'x64' && 'x64' || 'amd64_arm64' }}
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
cmake -S . -B build -G "Ninja Multi-Config" ^
-DGGML_BACKEND_DL=ON ^
-DLLAMA_BUILD_SERVER=ON ^
-DLLAMA_BUILD_BORINGSSL=ON ^
-DGGML_NATIVE=OFF ^
-DGGML_CPU=OFF ^
-DGGML_BACKEND_DL=ON ^
-DGGML_CPU_ALL_VARIANTS=ON ^
-DGGML_CUDA=ON ^
-DLLAMA_BUILD_BORINGSSL=ON ${{ matrix.defines }}
-DGGML_RPC=ON ^
-DGGML_CUDA_CUB_3DOT2=ON
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% --target ggml-cuda
cmake --build build --config Release -j %NINJA_JOBS% -t ggml
cmake --build build --config Release
- name: ccache-clear
uses: ./.github/actions/ccache-clear
with:
key: release-windows-2022-${{ matrix.arch }}-cuda-${{ matrix.cuda }}
key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
hip:
runs-on: windows-2022
@@ -158,7 +146,7 @@ jobs:
& "${env:HIP_PATH}\lib\llvm\bin\clang.exe" --version
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
# TODO: this build does not match the build in release.yml, so we use a different cache key
# ideally, the builds should match, similar to the CUDA build above so that we would be able
+11 -54
View File
@@ -19,18 +19,9 @@ on:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-ibm.yml',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-zdnn/**',
'ggml/src/ggml-quants.c',
'src/llama-quant.cpp',
'gguf-py/gguf/scripts/gguf_convert_endian.py',
'tests/test-quantize-be.sh'
'ggml/src/ggml-cpu/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -43,14 +34,9 @@ env:
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-26-s390x:
name: ubuntu-26-s390x (VXE ${{ matrix.vxe }})
runs-on: ubuntu-26.04-s390x
strategy:
fail-fast: false
matrix:
vxe: ["ON", "OFF"] # `-DGGML_VXE=ON/OFF`
ubuntu-24-s390x:
runs-on: ubuntu-24.04-s390x
steps:
- name: Clone
@@ -66,6 +52,12 @@ jobs:
libjpeg-dev build-essential libssl-dev \
git-lfs
- name: Toolchain workaround (GCC 14)
run: |
sudo apt-get install -y gcc-14 g++-14
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: Python Dependencies
id: python_depends
run: |
@@ -85,8 +77,7 @@ jobs:
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_RPC=ON \
-DGGML_VXE=${{ matrix.vxe }}
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
@@ -100,43 +91,9 @@ jobs:
run: |
cd build
echo "Fetch llama2c big-endian model"
wget https://huggingface.co/ggml-org-dev/stories260K/resolve/main/stories260K-be.gguf
wget https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories260K-be.gguf
./bin/llama-completion -m stories260K-be.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
- name: Test quantize (s390x)
id: quantize_test_s390x
run: |
./tests/test-quantize-be.sh ./build/bin/llama-quantize ./build/bin/llama-perplexity 2>&1
ubuntu-26-zdnn-s390x:
name: ubuntu-26-zdnn-s390x
runs-on: ubuntu-26.04-s390x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build Dependencies
id: build_depends
run: |
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
build-essential libssl-dev libzdnn-dev
- name: Build with zDNN Backend
id: cmake_build
run: |
cmake -B build \
-DLLAMA_FATAL_WARNINGS=ON \
-DGGML_NATIVE=OFF \
-DGGML_VXE=ON \
-DGGML_ZDNN=ON \
-DGGML_RPC=ON \
-DCMAKE_C_FLAGS="-march=arch15" \
-DCMAKE_CXX_FLAGS="-march=arch15"
time cmake --build build --config Release -j $(nproc)
ubuntu-24-ppc64le:
runs-on: ubuntu-24.04-ppc64le
+1 -5
View File
@@ -8,10 +8,6 @@ on:
schedule:
- cron: '0 0 * * 0'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -39,7 +35,7 @@ jobs:
uses: actions/checkout@v6
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.24
# uses: ggml-org/ccache-action@v1.2.16
# with:
# key: msys-windows-2025-x64
# variant: ccache
+1 -16
View File
@@ -23,11 +23,6 @@ on:
'ggml/src/ggml-opencl/**'
]
cache-mode: write
permissions:
actions: write
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -49,7 +44,7 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
key: opencl-windows-2025-x64
variant: ccache
@@ -85,13 +80,3 @@ jobs:
run: |
cmake -S . -B build -G "Ninja Multi-Config" -D CMAKE_TOOLCHAIN_FILE=cmake/arm64-windows-llvm.cmake -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/opencl-arm64-release" -DGGML_OPENCL=ON -DGGML_OPENCL_USE_ADRENO_KERNELS=ON -DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: opencl-windows-2025-x64
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
+13 -31
View File
@@ -22,10 +22,6 @@ on:
'ggml/src/ggml-openvino/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -36,17 +32,15 @@ env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
# TODO: fix failing tests on OpenVINO backend
CTEST_EXCLUDE: "test-llama-archs|test-llama-context|test-fp8-kv"
jobs:
ubuntu-24-openvino:
runs-on: [self-hosted, Linux, Intel, OpenVINO]
env:
# Sync versions in build-openvino.yml, ci-self-hosted-openvino.yml, release.yml, release-publish.yml, build-cache.yml, .devops/openvino.Dockerfile, docs/backend/OPENVINO.md
OPENVINO_VERSION_MAJOR: "2026.4.1"
OPENVINO_VERSION_FULL: "2026.4.1.22982.07f9c262b05"
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
@@ -84,29 +78,26 @@ jobs:
- name: Test (CPU)
id: cmake_test_cpu
# TODO: fix and re-enable the `test-llama-archs` test below
run: |
cd ${{ github.workspace }}
ctest --test-dir build/ReleaseOV -L main -E "${{ env.CTEST_EXCLUDE }}" --verbose --timeout 3000
ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 2000
- name: Test (GPU)
id: cmake_test_gpu
# TODO: fix and re-enable the `test-llama-archs` test below
run: |
cd ${{ github.workspace }}
export GGML_OPENVINO_DEVICE=GPU
ctest --test-dir build/ReleaseOV -L main -E "${{ env.CTEST_EXCLUDE }}" --verbose --timeout 3000
ctest --test-dir build/ReleaseOV -L main -E "test-llama-archs" --verbose --timeout 3000
openvino-windows-2022:
runs-on: windows-2022
cache-mode: write
permissions:
actions: write
contents: read
env:
# Sync versions in build-openvino.yml, ci-self-hosted-openvino.yml, release.yml, release-publish.yml, build-cache.yml, .devops/openvino.Dockerfile, docs/backend/OPENVINO.md
OPENVINO_VERSION_MAJOR: "2026.4.1"
OPENVINO_VERSION_FULL: "2026.4.1.22982.07f9c262b05"
# Sync versions in build-openvino.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
@@ -114,7 +105,7 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
key: openvino-windows-2022
variant: ccache
@@ -168,20 +159,11 @@ jobs:
- name: Test (CPU)
id: cmake_test_cpu
shell: cmd
# TODO: fix and re-enable the `test-llama-archs` test below
run: |
REM Find extracted OpenVINO folder dynamically
for /d %%i in (openvino_toolkit\*) do set OPENVINO_ROOT=%%i
call "%OPENVINO_ROOT%\setupvars.bat"
cd build
ctest --test-dir ReleaseOV -L main -E "${{ env.CTEST_EXCLUDE }}" -C Release --verbose --timeout 3000
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: openvino-windows-2022
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
ctest --test-dir ReleaseOV -L main -E "test-llama-archs" -C Release --verbose --timeout 3000
+81 -5
View File
@@ -22,10 +22,6 @@ on:
'ggml/src/ggml-cpu/arch/riscv/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -71,7 +67,7 @@ jobs:
# note: sparing some ccache since these jobs run on dedicated runners that are not part of the organitzation
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.24
# uses: ggml-org/ccache-action@afde29e5b5422e5da23cb1f639e8baecadeadfc3 # https://github.com/ggml-org/ccache-action/pull/1
# with:
# key: riscv-ubuntu-native
# evict-old-files: 1d
@@ -110,3 +106,83 @@ jobs:
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
ubuntu-riscv64-native-sanitizer:
runs-on: ubuntu-24.04-riscv
continue-on-error: true
strategy:
matrix:
sanitizer: [ADDRESS, THREAD, UNDEFINED]
build_type: [Debug]
steps:
- name: Install dependencies
run: |
# Set gcc-14 and g++-14 as the default compilers
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-14 100
sudo update-alternatives --install /usr/bin/g++ g++ /usr/bin/g++-14 100
git lfs install
- name: GCC version check
run: |
gcc --version
g++ --version
- name: Clone
id: checkout
uses: actions/checkout@v6
# note: sparing some ccache since these jobs run on dedicated runners that are not part of the organitzation
#- name: ccache
# uses: ggml-org/ccache-action@afde29e5b5422e5da23cb1f639e8baecadeadfc3 # https://github.com/ggml-org/ccache-action/pull/1
# with:
# key: riscv-ubuntu-native-sanitizer-${{ matrix.sanitizer }}-${{ matrix.build_type }}
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
if: ${{ matrix.sanitizer != 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=ON \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Build (no OpenMP)
id: cmake_build_no_openmp
if: ${{ matrix.sanitizer == 'THREAD' }}
run: |
cmake -B build \
-DLLAMA_OPENSSL=OFF \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DCMAKE_C_COMPILER=riscv64-linux-gnu-gcc-14 \
-DCMAKE_CXX_COMPILER=riscv64-linux-gnu-g++-14
cmake --build build --config ${{ matrix.build_type }} -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
+66
View File
@@ -0,0 +1,66 @@
name: CI (rpc)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-rpc.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-rpc.yml',
'ggml/src/ggml-rpc/**'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-24-rpc:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
continue-on-error: true
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libssl-dev ninja-build
- name: Build
id: cmake_build
run: |
cmake -B build \
-G "Ninja" \
-DCMAKE_BUILD_TYPE=Release \
-DGGML_RPC=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose
+27 -33
View File
@@ -21,10 +21,6 @@ on:
'.github/workflows/build-sanitize.yml'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -43,12 +39,13 @@ jobs:
strategy:
matrix:
include:
# thread and address doesn't run properly on some self hosted machines, so run it on Github instead
- sanitizer: ADDRESS
machine: ubuntu-26.04
machine: ubuntu-24.04
- sanitizer: THREAD
machine: ubuntu-26.04
machine: ubuntu-24.04
- sanitizer: UNDEFINED
machine: ubuntu-26.04
machine: [self-hosted, X64, Linux]
runs-on: ${{ matrix.machine }}
@@ -57,24 +54,31 @@ jobs:
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# if: ${{ matrix.sanitizer != 'UNDEFINED' }}
# with:
# key: ctest-${{ matrix.sanitizer }}-ubuntu-24.04
# variant: ccache
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: ctest-sanitizer-${{ matrix.sanitizer }}
folder: llama.cpp
hf_bucket: ggml-org/cache
# with UNDEFINED sanitizer, we have to build in Debug to avoid GCC 13 false-positive warnings
- name: Build (undefined)
id: cmake_build_undefined
if: ${{ matrix.sanitizer == 'UNDEFINED' }}
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Debug \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \
-DGGML_SANITIZE_${{ matrix.sanitizer }}=ON
cmake --build build --config Debug -j $(nproc)
- name: Build
id: cmake_build
if: ${{ matrix.sanitizer == 'ADDRESS' || matrix.sanitizer == 'UNDEFINED' }}
if: ${{ matrix.sanitizer == 'ADDRESS' }}
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=RelWithDebInfo \
@@ -95,20 +99,10 @@ jobs:
cmake --build build --config RelWithDebInfo -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: ctest-sanitizer-${{ matrix.sanitizer }}
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Test
id: cmake_test
# skip run in Debug - very slow
if: ${{ matrix.sanitizer != 'UNDEFINED' }}
run: |
cd build
ctest -L main -E tokenizer --verbose --timeout 900
+409
View File
@@ -0,0 +1,409 @@
name: CI (self-hosted)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-self-hosted.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl',
'**/*.wgsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-self-hosted.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh',
'**/*.swift',
'**/*.m',
'**/*.metal',
'**/*.comp',
'**/*.glsl',
'**/*.wgsl'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-cuda:
runs-on: [self-hosted, Linux, NVIDIA]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
nvidia-smi
GG_BUILD_CUDA=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-rocm:
runs-on: [self-hosted, Linux, AMD]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
# HIP_LAUNCH_BLOCKING=1: workaround for an async-execution correctness
# issue on integrated RDNA3.5 (gfx1151) where batched inference returns
# incorrect output (perplexity ~88 vs ~9.4). Serializing kernel launches
# restores correctness. Remove once the underlying ROCm/HIP issue is fixed.
env:
HIP_LAUNCH_BLOCKING: "1"
run: |
rocminfo
GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS=gfx1151 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-nvidia-cm:
runs-on: [self-hosted, Linux, NVIDIA]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-nvidia-cm2:
runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-webgpu-nvidia:
runs-on: [self-hosted, Linux, NVIDIA, X64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 \
GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMX-compatible machine
#cpu-amx:
# runs-on: [self-hosted, Linux, CPU, AMX]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMD GPU machine
# amd-vulkan:
# runs-on: [self-hosted, Linux, AMD]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# vulkaninfo --summary
# GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMD GPU machine
# amd-rocm:
# runs-on: [self-hosted, Linux, AMD]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# amd-smi static
# GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-metal:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-webgpu-apple:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-apple:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-intel-linux:
runs-on: [self-hosted, Linux, Intel]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
persist-credentials: false
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-intel-windows:
runs-on: [self-hosted, Windows, X64, Intel]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
shell: C:\msys64\usr\bin\bash.exe --noprofile --norc -eo pipefail "{0}"
env:
MSYSTEM: UCRT64
CHERE_INVOKING: 1
PATH: C:\msys64\ucrt64\bin;C:\msys64\usr\bin;C:\Windows\System32;${{ env.PATH }}
run: |
vulkaninfo --summary
# Skip python related tests with GG_BUILD_LOW_PERF=1 since Windows MSYS2 UCRT64 currently fails to create
# a valid python environment for testing
LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp
gpu-openvino-low-perf:
runs-on: [self-hosted, Linux, Intel, OpenVINO]
env:
# Sync versions in build.yml, build-self-hosted.yml, release.yml, build-cache.yml, .devops/openvino.Dockerfile
OPENVINO_VERSION_MAJOR: "2026.2.1"
OPENVINO_VERSION_FULL: "2026.2.1.21919.ede283a88e3"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup OpenVINO Toolkit
uses: ./.github/actions/linux-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
- name: Install OpenVINO dependencies
run: |
cd ./openvino_toolkit
chmod +x ./install_dependencies/install_openvino_dependencies.sh
echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh
- name: Test
id: ggml-ci
run: |
source ./openvino_toolkit/setupvars.sh
GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
cpu-x64-high-perf:
runs-on: [self-hosted, Linux, X64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
cpu-arm64-high-perf-graviton4:
runs-on: ah-ubuntu_22_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
cpu-arm64-graviton4-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Test
id: ggml-ci
run: |
GG_BUILD_KLEIDIAI=1 \
GG_BUILD_EXTRA_TESTS_0=1 \
bash ./ci/run.sh ./tmp/results ./tmp/mnt
+20 -79
View File
@@ -22,10 +22,6 @@ on:
'ggml/src/ggml-sycl/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -38,7 +34,7 @@ env:
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-26-sycl:
ubuntu-24-sycl:
strategy:
matrix:
build: [fp32, fp16]
@@ -48,12 +44,12 @@ jobs:
- build: fp16
fp16: ON
runs-on: ubuntu-26.04
runs-on: ubuntu-24.04
env:
ONEAPI_ROOT: /opt/intel/oneapi/
ONEAPI_INSTALLER_VERSION: "2026.2"
LEVEL_ZERO_VERSION: "1.34.0"
ONEAPI_INSTALLER_VERSION: "2025.3.3"
LEVEL_ZERO_VERSION: "1.28.2"
LEVEL_ZERO_UBUNTU_VERSION: "u24.04"
continue-on-error: true
@@ -67,45 +63,23 @@ jobs:
shell: bash
run: |
cd /tmp
echo "Download oneAPI Deep Learning Essentials installation package"
wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/aef232d2-aac5-4cd6-bceb-911019bbb6a8/intel-deep-learning-essentials-2026.2.0.640_offline.sh -O intel-deep-learning-essentials_offline.sh
echo "Install oneAPI Deep Learning Essentials components"
wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/56f7923a-adb8-43f3-8b02-2b60fcac8cab/intel-deep-learning-essentials-2025.3.3.16_offline.sh -O intel-deep-learning-essentials_offline.sh
sudo bash intel-deep-learning-essentials_offline.sh -s -a --silent --eula accept
echo "Download oneDNN installation package"
wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/46452a4a-7b7f-49f2-be4c-602a900180bb/intel-onednn-2026.1.0.625_offline.sh -O intel-onednn_offline.sh
echo "Install oneDNN components"
sudo bash intel-onednn_offline.sh -s -a --silent --eula accept
- name: Install Level Zero SDK
shell: bash
run: |
cd /tmp
# v1.33.x renamed the Debian packages to libze1 / libze-dev
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/libze1_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O libze1.deb
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/libze-dev_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O libze-dev.deb
sudo apt-get install -y ./libze1.deb ./libze-dev.deb
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install -y libssl-dev
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb
wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb
sudo apt-get install -y ./level-zero.deb ./level-zero-devel.deb
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: sycl-ubuntu-26-${{ matrix.build }}
folder: llama.cpp
hf_bucket: ggml-org/cache
key: sycl-ubuntu-24-${{ matrix.build }}
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
@@ -117,46 +91,24 @@ jobs:
-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx \
-DLLAMA_OPENSSL=OFF \
-DGGML_NATIVE=OFF \
-DGGML_SYCL_F16=${{ matrix.fp16 }} \
-DGGML_SYCL_SUPPORT_LEVEL_ZERO_API=ON \
-DGGML_SYCL_DNN=ON \
-DCMAKE_CXX_FLAGS="-fsycl-unnamed-lambda" \
-DCMAKE_EXE_LINKER_FLAGS="-fsycl-unnamed-lambda"
-DGGML_SYCL_F16=${{ matrix.fp16 }}
time cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: sycl-ubuntu-26-${{ matrix.build }}
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
windows-latest-sycl:
runs-on: windows-2022
cache-mode: write
permissions:
actions: write
contents: read
defaults:
run:
shell: bash
env:
WINDOWS_DLE_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b177a006-5cd9-4cb2-807f-8199cc73d53c/intel-deep-learning-essentials-2026.2.0.638_offline.exe
WINDOWS_ONEDNN_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/8f905666-c85c-43fb-9bd0-2618c7ecd33b/intel-onednn-2026.1.0.622_offline.exe
WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.tbb.devel
WINDOWS_DNNL: intel.oneapi.win.dnnl
LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.34.0/level-zero-win-sdk-1.34.0.zip
WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/b60765d1-2b85-4e85-86b6-cb0e9563a699/intel-deep-learning-essentials-2025.3.3.18_offline.exe
WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel:intel.oneapi.win.dnnl:intel.oneapi.win.tbb.devel
LEVEL_ZERO_SDK_URL: https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero-win-sdk-1.28.2.zip
ONEAPI_ROOT: "C:/Program Files (x86)/Intel/oneAPI"
ONEAPI_INSTALLER_VERSION: "2026.2"
ONEAPI_INSTALLER_VERSION: "2025.3.3"
steps:
- name: Clone
id: checkout
@@ -165,8 +117,7 @@ jobs:
- name: Download & Install oneAPI
shell: bash
run: |
scripts/install-oneapi.bat $WINDOWS_DLE_URL $WINDOWS_DPCPP_MKL
scripts/install-oneapi.bat $WINDOWS_ONEDNN_URL $WINDOWS_DNNL
scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
- name: Install Level Zero SDK
shell: pwsh
@@ -176,7 +127,7 @@ jobs:
"LEVEL_ZERO_V1_SDK_PATH=C:/level-zero-sdk" | Out-File -FilePath $env:GITHUB_ENV -Append
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
key: sycl-windows-latest
variant: ccache
@@ -188,13 +139,3 @@ jobs:
- name: Build
id: cmake_build
run: examples/sycl/win-build-sycl.bat
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: sycl-windows-latest
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
+2 -6
View File
@@ -22,17 +22,13 @@ on:
'ggml/src/ggml-virtgpu/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
ubuntu-26-virtgpu:
runs-on: ${{ 'ubuntu-26.04-arm' || 'ubuntu-26.04' }}
ubuntu-24-virtgpu:
runs-on: ${{ 'ubuntu-24.04-arm' || 'ubuntu-24.04' }}
steps:
- name: Clone
+27 -138
View File
@@ -24,10 +24,6 @@ on:
'ggml/src/ggml-vulkan/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -35,14 +31,13 @@ concurrency:
env:
GGML_NLOOP: 3
GGML_N_THREADS: 1
GGML_SCHED_DEBUG_REALLOC: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
ubuntu-arm64:
runs-on: ubuntu-26.04-arm
runs-on: ubuntu-24.04-arm
steps:
- name: Clone
@@ -53,23 +48,17 @@ jobs:
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential glslc libvulkan-dev spirv-headers libssl-dev ninja-build
sudo apt-get install -y gcc-14 g++-14 build-essential glslc libvulkan-dev spirv-headers libssl-dev ninja-build
echo "CC=gcc-14" >> "$GITHUB_ENV"
echo "CXX=g++-14" >> "$GITHUB_ENV"
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
key: vulkan-ubuntu-24.04-arm-new
variant: ccache
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: vulkan-ubuntu-26.04-arm
folder: llama.cpp
hf_bucket: ggml-org/cache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Configure
id: cmake_configure
@@ -84,20 +73,8 @@ jobs:
run: |
time cmake --build build -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: vulkan-ubuntu-26.04-arm
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
ubuntu-llvmpipe:
runs-on: ubuntu-26.04
runs-on: ubuntu-24.04
steps:
- name: Clone
@@ -116,28 +93,26 @@ jobs:
run: |
echo "VULKAN_SDK_VERSION=$(curl https://vulkan.lunarg.com/sdk/latest/linux.txt)" >> "$GITHUB_ENV"
- name: Setup Vulkan SDK
id: setup
uses: ./.github/actions/unarchive-tar
- name: Use Vulkan SDK Cache
uses: actions/cache@v5
id: cache-sdk
with:
url: https://sdk.lunarg.com/sdk/download/${{ env.VULKAN_SDK_VERSION }}/linux/vulkan_sdk.tar.xz
path: ./vulkan_sdk
strip: 1
key: cache-gha-vulkan-sdk-${{ env.VULKAN_SDK_VERSION }}-${{ runner.os }}
- name: Setup Vulkan SDK
if: steps.cache-sdk.outputs.cache-hit != 'true'
uses: ./.github/actions/linux-setup-vulkan
with:
path: ./vulkan_sdk
version: ${{ env.VULKAN_SDK_VERSION }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: vulkan-ubuntu-26.04-llvmpipe
folder: llama.cpp
hf_bucket: ggml-org/cache
key: vulkan-ubuntu-24.04-llvmpipe
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
@@ -148,18 +123,6 @@ jobs:
-DGGML_VULKAN=ON
cmake --build build --config Release -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: vulkan-ubuntu-26.04-llvmpipe
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Test
id: cmake_test
run: |
@@ -167,80 +130,6 @@ jobs:
export GGML_VK_VISIBLE_DEVICES=0
export GGML_VK_DISABLE_F16=1
export GGML_VK_DISABLE_COOPMAT=1
ctest -L main --verbose --timeout 900
windows:
name: windows / ${{ matrix.arch }}
runs-on: windows-2025
cache-mode: write
permissions:
actions: write
contents: read
strategy:
matrix:
include:
- arch: 'x64'
- arch: 'arm64'
env:
VULKAN_VERSION: 1.4.357.0
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
key: cpu-windows-2025-${{ matrix.arch }}-vulkan
variant: ccache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Install Vulkan SDK
id: get_vulkan
run: |
curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
& "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install ${{ matrix.arch == 'arm64' && 'com.lunarg.vulkan.arm64' || '' }}
Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"
- name: Install Ninja
id: install_ninja
run: |
choco install ninja
- name: Build
id: cmake_build
run: |
cmake -S . -B build -G "Ninja Multi-Config" `
-D CMAKE_TOOLCHAIN_FILE=cmake/${{ matrix.arch }}-windows-llvm.cmake `
-DCMAKE_BUILD_TYPE=Release `
-DGGML_NATIVE=OFF `
-DLLAMA_BUILD_SERVER=ON `
-DGGML_RPC=ON `
-DGGML_BACKEND_DL=ON `
-DGGML_CPU_ALL_VARIANTS=${{ matrix.arch == 'x64' && 'ON' || 'OFF' }} `
-DGGML_VULKAN=ON `
-DLLAMA_BUILD_BORINGSSL=ON
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Test
if: ${{ matrix.arch == 'x64' }}
id: cmake_test
run: |
cd build
ctest -L main -C Release --verbose --timeout 900
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: cpu-windows-2025-${{ matrix.arch }}-vulkan
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
# This is using llvmpipe and runs slower than other backends
# test-backend-ops is too slow on llvmpipe, skip it
ctest -L main -E test-backend-ops --verbose --timeout 900
-142
View File
@@ -1,142 +0,0 @@
name: CI (wasi)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/build-wasi.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.wgsl',
'**/*.tmpl',
'ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/build-wasi.yml',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.wgsl',
'**/*.tmpl',
'ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
WASI_SDK_VERSION: 34
DAWN_VERSION: v20260908.214631
DAWN_COMMIT: 94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655
WASI_WEBGPU_HEADERS_COMMIT: 917765edd7cb8f8cf95bda1217514c78f71b582b
jobs:
ubuntu-webgpu:
runs-on: ubuntu-26.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: Install wasi-sdk
uses: bytecodealliance/setup-wasi-sdk-action@77d09f3df1e8da344d8403cf8631af8977938b4c # v1.0.0
with:
version: ${{ env.WASI_SDK_VERSION }}
add-to-path: false
- name: wasi:webgpu Dependency
run: |
mkdir -p wasi-webgpu/dawn-headers
curl -fL "https://github.com/google/dawn/releases/download/${DAWN_VERSION}/dawn-headers-${DAWN_COMMIT}.tar.gz" |
tar -xz -C wasi-webgpu/dawn-headers --strip-components=1
git init -q wasi-webgpu/wasi-webgpu-headers
cd wasi-webgpu/wasi-webgpu-headers
git fetch -q --depth 1 https://github.com/wasi-gfx/wasi-webgpu-headers.git ${WASI_WEBGPU_HEADERS_COMMIT}
git checkout -q FETCH_HEAD
git submodule update -q --init --depth 1
cd ../..
# ggml-webgpu does find_package(Dawn) and links dawn::webgpu_dawn. There is no Dawn on WASI,
# so this target instead compiles wasi-webgpu-headers (webgpu.h over wasi:webgpu imports)
# and exposes Dawn's webgpu_cpp.h on top of it.
cat > wasi-webgpu/DawnConfig.cmake << 'EOF'
set(_wasi_webgpu "${CMAKE_CURRENT_LIST_DIR}/wasi-webgpu-headers")
add_library(dawn::webgpu_dawn INTERFACE IMPORTED)
set_target_properties(dawn::webgpu_dawn PROPERTIES
INTERFACE_SOURCES "${_wasi_webgpu}/webgpu.c;${_wasi_webgpu}/async_futures.c;${_wasi_webgpu}/imports.c;${_wasi_webgpu}/imports_component_type.o"
INTERFACE_INCLUDE_DIRECTORIES "${CMAKE_CURRENT_LIST_DIR}/dawn-headers/include/webgpu_upstream;${_wasi_webgpu}")
EOF
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: webgpu-ubuntu-26.04-arm-wasi
folder: llama.cpp
hf_bucket: ggml-org/cache
# llama-common does not build for WASI, so the executables are linked by hand
- name: Build
id: cmake_build
run: |
WASI_FLAGS="-msimd128 -D_WASI_EMULATED_SIGNAL -fwasm-exceptions -mllvm -wasm-use-legacy-eh=false"
cmake -B build-wasi \
-G "Ninja" \
-DCMAKE_TOOLCHAIN_FILE=${WASI_SDK_PATH}/share/cmake/wasi-sdk-p3.cmake \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_C_FLAGS="${WASI_FLAGS}" \
-DCMAKE_CXX_FLAGS="${WASI_FLAGS}" \
-DCMAKE_HAVE_LIBC_PTHREAD=1 \
-DBUILD_SHARED_LIBS=OFF \
-DGGML_NATIVE=OFF \
-DGGML_OPENMP=OFF \
-DGGML_WEBGPU=ON \
-DDawn_DIR=$PWD/wasi-webgpu \
-DLLAMA_BUILD_COMMON=OFF
time cmake --build build-wasi --config Release --target llama -j $(nproc)
LIBS="build-wasi/ggml/src/libggml.a build-wasi/ggml/src/ggml-webgpu/libggml-webgpu.a build-wasi/ggml/src/libggml-cpu.a build-wasi/ggml/src/libggml-base.a"
LDFLAGS="-lunwind -ldl -Wl,-z,stack-size=8388608"
CXX="${WASI_SDK_PATH}/bin/clang++ --target=wasm32-wasip3 -O3 -std=c++17 ${WASI_FLAGS} -I include -I ggml/include"
$CXX examples/simple/simple.cpp build-wasi/src/libllama.a $LIBS $LDFLAGS -o build-wasi/llama-simple.wasm
$CXX tests/test-backend-ops.cpp $LIBS $LDFLAGS -o build-wasi/test-backend-ops.wasm
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: webgpu-ubuntu-26.04-arm-wasi
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
+6 -30
View File
@@ -33,10 +33,6 @@ on:
'ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -50,7 +46,7 @@ env:
jobs:
ubuntu-webgpu:
runs-on: ubuntu-26.04-arm
runs-on: ubuntu-24.04-arm
steps:
- name: Clone
@@ -58,10 +54,11 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
save: false
key: webgpu-ubuntu-24.04-arm-wasm
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Install Emscripten
run: |
@@ -72,22 +69,13 @@ jobs:
- name: Fetch emdawnwebgpu
run: |
DAWN_TAG="v20260908.214631"
DAWN_TAG="v20260317.182325"
EMDAWN_PKG="emdawnwebgpu_pkg-${DAWN_TAG}.zip"
echo "Downloading ${EMDAWN_PKG}"
curl -L -o emdawn.zip \
"https://github.com/google/dawn/releases/download/${DAWN_TAG}/${EMDAWN_PKG}"
unzip emdawn.zip
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: webgpu-ubuntu-26.04-arm-wasm
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build WASM WebGPU
run: |
source emsdk/emsdk_env.sh
@@ -100,15 +88,3 @@ jobs:
-DEMDAWNWEBGPU_DIR=emdawnwebgpu_pkg
time cmake --build build-wasm --config Release --target test-backend-ops -j $(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: webgpu-ubuntu-26.04-arm-wasm
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
+105 -7
View File
@@ -7,7 +7,15 @@ on:
- master
paths: [
'.github/workflows/build-webgpu.yml',
'ggml/src/ggml-webgpu/**'
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.wgsl',
'**/*.tmpl',
'ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py'
]
pull_request:
@@ -17,10 +25,6 @@ on:
'ggml/src/ggml-webgpu/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -34,7 +38,7 @@ env:
jobs:
format:
runs-on: ubuntu-26.04
runs-on: ubuntu-24.04
steps:
- name: Clone
@@ -45,7 +49,7 @@ jobs:
wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key |
sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
sudo add-apt-repository -y \
"deb http://apt.llvm.org/resolute/ llvm-toolchain-resolute-22 main"
"deb http://apt.llvm.org/noble/ llvm-toolchain-noble-22 main"
sudo apt-get update
sudo apt-get install -y clang-format-22
@@ -55,3 +59,97 @@ jobs:
-type f \( -name '*.cpp' -o -name '*.hpp' -o -name '*.h' \) \
-print0 |
xargs -0 clang-format-22 --dry-run --Werror
macos:
runs-on: macos-latest
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: webgpu-macos-latest
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-macos-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Build
id: cmake_build
run: |
export CMAKE_PREFIX_PATH=dawn
cmake -B build -G "Ninja" -DCMAKE_BUILD_TYPE=Release -DGGML_WEBGPU=ON -DGGML_METAL=OFF -DGGML_BLAS=OFF
time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu)
- name: Test
id: cmake_test
run: |
cd build
ctest -L main --verbose --timeout 900
ubuntu:
runs-on: ubuntu-24.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: webgpu-ubuntu-24.04
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Dependencies
id: depends
run: |
sudo add-apt-repository -y ppa:kisak/kisak-mesa
sudo apt-get update -y
sudo apt-get install -y build-essential mesa-vulkan-drivers \
libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libssl-dev
- name: Dawn Dependency
id: dawn-depends
run: |
sudo apt-get install -y libxrandr-dev libxinerama-dev libxcursor-dev mesa-common-dev libx11-xcb-dev libxi-dev
DAWN_VERSION="v20260317.182325"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-18eb229ef5f707c1464cc581252e7603c73a3ef0-ubuntu-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Build
id: cmake_build
run: |
export Dawn_DIR=dawn/lib64/cmake/Dawn
cmake -B build \
-DGGML_WEBGPU=ON
time cmake --build build --config Release -j $(nproc)
- name: Test
id: cmake_test
run: |
cd build
# This is using llvmpipe and runs slower than other backends
# test-backend-ops is too slow on llvmpipe, skip it
ctest -L main -E test-backend-ops --verbose --timeout 900
+1 -5
View File
@@ -17,13 +17,9 @@ on:
'scripts/sync_vendor.py'
]
cache-mode: none
permissions:
contents: read
jobs:
check-vendor:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast]
steps:
- name: Checkout
-153
View File
@@ -1,153 +0,0 @@
name: CI (self-hosted CPU backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-cpu.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-cpu.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
cpu-x64-high-perf:
runs-on: hf-jobs-cpu-upgrade:ubuntu26_04
# note: this runner has 8 CPUs, but std::thread::hardware_concurrency reports the cores of the
# host (https://github.com/ggml-org/llama.cpp/pull/31439#issuecomment-6683386059)
env:
TEST_ARG_HARDWARE_CONCURRENCY: 8
TEST_ARG_PARALLEL_WORKERS: 4
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
sudo apt update
sudo apt install -y build-essential cmake libssl-dev time unzip wget python3 python3-venv python3-dev
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: self-hosted-cpu-x64-high-perf
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_HIGH_PERF=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: self-hosted-cpu-x64-high-perf
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
cpu-arm64-high-perf-graviton4:
runs-on: ah-ubuntu_24_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) \
GG_BUILD_HIGH_PERF=1 \
GG_BUILD_NO_BF16=1 \
GG_BUILD_EXTRA_TESTS_0=1 \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
# TODO: provision AMX-compatible machine
#cpu-amx:
# runs-on: [self-hosted, Linux, CPU, AMX]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
-202
View File
@@ -1,202 +0,0 @@
name: CI (self-hosted CUDA backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-cuda.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.cuh'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-cuda.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-cuda/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-cuda:
runs-on: "hf-jobs-t4-medium:cuda13"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y cmake libssl-dev time unzip wget python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: self-hosted-gpu-cuda
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Test
id: ggml-ci
run: |
nvidia-smi
GG_BUILD_CUDA=1 CUDACXX=/usr/local/cuda/bin/nvcc bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: self-hosted-gpu-cuda
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
gpu-rocm:
strategy:
fail-fast: false
matrix:
include:
# Strix Halo (iGPU, RDNA3.5)
- gpu: gfx1151
runner: [self-hosted, Linux, strix-halo, devlab-dispatch]
# async-execution correctness workaround, gfx1151 only (see Test step)
hip_launch_blocking: "1"
# Radeon AI PRO R9700 (dGPU, RDNA4)
- gpu: gfx1201
runner: [self-hosted, Linux, radeon-r9700, devlab-dispatch]
hip_launch_blocking: "0"
# HIP-graph capture fails on gfx1201 (hipMemset -> hipErrorStreamCaptureImplicit)
disable_hip_graphs: true
name: gpu-rocm (${{ matrix.gpu }})
runs-on: ${{ matrix.runner }}
timeout-minutes: 120
env:
ROCM_VERSION: "10.0.0"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Verify GPU device
run: |
ls /dev/kfd /dev/dri/renderD* || { echo "ERROR: no amdgpu compute device"; exit 1; }
# same TheRock wheels as the ubuntu-24-rocm release build, so the runner does not need a ROCm install
- name: Setup TheRock with Wheels
run: |
python3 -m venv "$RUNNER_TEMP/rocm"
"$RUNNER_TEMP/rocm/bin/python" -m pip install --index-url https://stable.repo.amd.com/rocm/whl-next/ "rocm[libraries,devel,device-${{ matrix.gpu }}]==${ROCM_VERSION}"
ROCM_PATH=$("$RUNNER_TEMP/rocm/bin/rocm-sdk" path --root)
{
echo "ROCM_PATH=$ROCM_PATH"
echo "HIP_PATH=$ROCM_PATH"
echo "CMAKE_PREFIX_PATH=$("$RUNNER_TEMP/rocm/bin/rocm-sdk" path --cmake)"
echo "LD_LIBRARY_PATH=$ROCM_PATH/lib:${LD_LIBRARY_PATH:-}"
} >> "$GITHUB_ENV"
"$RUNNER_TEMP/rocm/bin/rocm-sdk" path --bin >> "$GITHUB_PATH"
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
# ROCm is installed again on each run, so hash the compiler content, not its mtime
- name: Tune ccache for reinstalled ROCm toolchain
run: |
ccache --set-config=compiler_check=content
ccache --set-config=sloppiness=time_macros,include_file_mtime,include_file_ctime
ccache --set-config=depend_mode=true
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: self-hosted-gpu-rocm-${{ matrix.gpu }}
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Test
id: ggml-ci
# HIP_LAUNCH_BLOCKING=1: workaround for an async-execution correctness
# issue on integrated RDNA3.5 (gfx1151) where batched inference returns
# incorrect output (perplexity ~88 vs ~9.4). Serializing kernel launches
# restores correctness. Remove once the underlying ROCm/HIP issue is fixed.
env:
HIP_LAUNCH_BLOCKING: ${{ matrix.hip_launch_blocking }}
run: |
rocminfo
# Exported rather than set in env:, because ggml only checks that the
# variable is defined: an empty value would disable graphs on gfx1151 too.
if [ "${{ matrix.disable_hip_graphs }}" = "true" ]; then export GGML_CUDA_DISABLE_GRAPHS=1; fi
GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS=${{ matrix.gpu }} bash ./ci/run.sh "$RUNNER_TEMP/results/llama.cpp" "$RUNNER_TEMP/mnt/llama.cpp"
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: self-hosted-gpu-rocm-${{ matrix.gpu }}
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
# TODO: provision AMD GPU machine
# amd-rocm:
# runs-on: [self-hosted, Linux, AMD]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# amd-smi static
# GG_BUILD_ROCM=1 GG_BUILD_AMDGPU_TARGETS="gfx1101" bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
@@ -1,89 +0,0 @@
name: CI (self-hosted KleidiAI backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-kleidiai.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-kleidiai.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
cpu-arm64-graviton4-kleidiai:
runs-on: ah-ubuntu_24_04-c8g_8x
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dependencies
id: depends
run: |
set -euxo pipefail
sudo apt-get update
sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \
apt-get install -y \
build-essential \
python3-venv \
gpg \
wget \
time \
git-lfs
git lfs install
# install the latest cmake
sudo install -d /usr/share/keyrings
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \
| gpg --dearmor \
| sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \
| sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt-get update
sudo apt-get install -y cmake
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) \
GG_BUILD_KLEIDIAI=1 \
GG_BUILD_EXTRA_TESTS_0=1 \
GG_BUILD_HIGH_PERF=1 \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
@@ -1,63 +0,0 @@
name: CI (self-hosted Metal backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-metal.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.swift',
'**/*.m',
'**/*.metal'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-metal.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-metal/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-metal:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
@@ -1,79 +0,0 @@
name: CI (self-hosted OpenVINO backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-openvino.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-openvino.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-openvino/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-openvino-low-perf:
runs-on: [self-hosted, Linux, Intel, OpenVINO]
env:
# Sync versions in build-openvino.yml, ci-self-hosted-openvino.yml, release.yml, release-publish.yml, build-cache.yml, .devops/openvino.Dockerfile, docs/backend/OPENVINO.md
OPENVINO_VERSION_MAJOR: "2026.4.1"
OPENVINO_VERSION_FULL: "2026.4.1.22982.07f9c262b05"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Setup OpenVINO Toolkit
uses: ./.github/actions/linux-setup-openvino
with:
path: ./openvino_toolkit
version_major: ${{ env.OPENVINO_VERSION_MAJOR }}
version_full: ${{ env.OPENVINO_VERSION_FULL }}
- name: Install OpenVINO dependencies
run: |
cd ./openvino_toolkit
chmod +x ./install_dependencies/install_openvino_dependencies.sh
echo "Y" | sudo -E ./install_dependencies/install_openvino_dependencies.sh
- name: Test
id: ggml-ci
run: |
source ./openvino_toolkit/setupvars.sh
GG_BUILD_OPENVINO=1 GGML_OPENVINO_DEVICE=GPU GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
-205
View File
@@ -1,205 +0,0 @@
name: CI (self-hosted Vulkan backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-vulkan.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.comp',
'**/*.glsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-vulkan.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-vulkan/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-vulkan-nvidia-cm:
# runs-on: "hf-jobs-t4-small:ubuntu26_04"
runs-on: [self-hosted, Linux, NVIDIA]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# - name: Install dependencies
# run: |
# sudo apt update
# sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan-dev glslc spirv-headers vulkan-tools mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 libssl-dev time unzip wget python3 python3-venv python3-pip
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.24
# with:
# restore: false
# save: false
# - name: ccache-buckets-restore
# uses: ./.github/actions/ccache-buckets
# with:
# key: self-hosted-vulkan-nvidia-cm
# folder: llama.cpp
# hf_bucket: ggml-org/cache
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 GGML_VK_DISABLE_COOPMAT2=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
# - name: ccache-buckets-save
# if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
# uses: ./.github/actions/ccache-buckets
# env:
# HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
# with:
# key: self-hosted-vulkan-nvidia-cm
# folder: llama.cpp
# evict-old-files: 1d
# hf_bucket: ggml-org/cache
# save: true
gpu-vulkan-nvidia-cm2:
# runs-on: "hf-jobs-t4-small:ubuntu26_04"
runs-on: [self-hosted, Linux, NVIDIA, COOPMAT2]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
# - name: Install dependencies
# run: |
# sudo apt update
# sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan-dev glslc spirv-headers vulkan-tools mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 libssl-dev time unzip wget python3 python3-venv python3-pip
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.24
# with:
# restore: false
# save: false
# - name: ccache-buckets-restore
# uses: ./.github/actions/ccache-buckets
# with:
# key: self-hosted-vulkan-nvidia-cm2
# folder: llama.cpp
# hf_bucket: ggml-org/cache
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
# - name: ccache-buckets-save
# if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
# uses: ./.github/actions/ccache-buckets
# env:
# HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
# with:
# key: self-hosted-vulkan-nvidia-cm2
# folder: llama.cpp
# evict-old-files: 1d
# hf_bucket: ggml-org/cache
# save: true
gpu-vulkan-apple:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
gpu-vulkan-intel-linux:
runs-on: [self-hosted, Linux, Intel]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
persist-credentials: false
- name: Test
id: ggml-ci
run: |
vulkaninfo --summary
GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
gpu-vulkan-intel-windows:
runs-on: [self-hosted, Windows, X64, Intel]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Test
id: ggml-ci
shell: C:\msys64\usr\bin\bash.exe --noprofile --norc -eo pipefail "{0}"
env:
MSYSTEM: UCRT64
CHERE_INVOKING: 1
PATH: C:\msys64\ucrt64\bin;C:\msys64\usr\bin;C:\Windows\System32;${{ env.PATH }}
run: |
vulkaninfo --summary
# Skip python related tests with GG_BUILD_LOW_PERF=1 since Windows MSYS2 UCRT64 currently fails to create
# a valid python environment for testing
LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp
# TODO: provision AMD GPU machine
# amd-vulkan:
# runs-on: [self-hosted, Linux, AMD]
# steps:
# - name: Clone
# id: checkout
# uses: actions/checkout@v6
# - name: Test
# id: ggml-ci
# run: |
# vulkaninfo --summary
# GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
-134
View File
@@ -1,134 +0,0 @@
name: CI (self-hosted WebGPU backend)
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/ci-self-hosted-webgpu.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.wgsl'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ci-self-hosted-webgpu.yml',
'ci/run.sh',
'**/CMakeLists.txt',
'**/.cmake',
'ggml/src/*',
'ggml/src/ggml-cpu/**',
'ggml/src/ggml-webgpu/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
gpu-webgpu-nvidia:
runs-on: "hf-jobs-t4-small:ubuntu26_04"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan1 mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 libssl-dev time unzip wget python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: self-hosted-webgpu-nvidia
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260908.214631"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-ubuntu-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 \
GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
GG_BUILD_WEBGPU_DAWN_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: self-hosted-webgpu-nvidia
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
gpu-webgpu-apple:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260908.214631"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-macos-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Test
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
+3 -2
View File
@@ -3,9 +3,10 @@ on:
schedule:
- cron: "42 0 * * *"
cache-mode: none
# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
contents: read
issues: write
jobs:
close-issues:
+1 -5
View File
@@ -9,17 +9,13 @@ on:
branches:
- master
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
model-naming:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast]
steps:
- uses: actions/checkout@v6
- name: Check model naming conventions
+4 -6
View File
@@ -11,12 +11,10 @@ on:
paths:
- .github/workflows/copilot-setup-steps.yml
cache-mode: none
jobs:
# The job MUST be called `copilot-setup-steps` or it will not be picked up by Copilot.
copilot-setup-steps:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# Set the permissions to the lowest permissions possible needed for your steps.
# Copilot will be given its own token for its operations.
@@ -31,10 +29,10 @@ jobs:
uses: actions/checkout@v6
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
save: false
key: copilot-setup-steps
evict-old-files: 1d
- name: Dependencies
id: depends
+28 -86
View File
@@ -16,22 +16,19 @@ on:
description: "Skip the s390x build target (useful for fast test runs that do not need the IBM Z runner)"
type: boolean
default: false
skip_ref_check:
description: "Skip the requirement to run from a tag (allows branch refs)"
type: boolean
default: false
schedule:
# Rebuild daily rather than on every push because it is expensive
- cron: '12 4 * * *'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
# Fine-grant permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
packages: write
jobs:
create_tag:
name: Create and push git tag
@@ -42,20 +39,11 @@ jobs:
source_tag: ${{ steps.srctag.outputs.name }}
steps:
- name: Check manual run ref
if: ${{ github.event_name == 'workflow_dispatch' && !inputs.skip_ref_check }}
run: |
if [[ "$GITHUB_REF_TYPE" != "tag" ]]; then
echo "::error::Manual runs of this workflow must be started from a tag"
exit 1
fi
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ssh-key: ${{ secrets.DEPLOY_KEY_RELEASE }}
- name: Determine source tag name
id: srctag
@@ -73,16 +61,13 @@ jobs:
build_ui:
name: Build UI
needs: create_tag
permissions:
actions: write
contents: read
uses: ./.github/workflows/ui-build.yml
with:
ui_version: ${{ needs.create_tag.outputs.source_tag }}
hf_ui_version: ${{ needs.create_tag.outputs.source_tag }}
prepare_matrices:
name: Prepare Docker matrices
runs-on: ubuntu-26.04
runs-on: ubuntu-24.04
outputs:
build_matrix: ${{ steps.matrices.outputs.build_matrix }}
merge_matrix: ${{ steps.matrices.outputs.merge_matrix }}
@@ -99,19 +84,19 @@ jobs:
# Keep all build targets in one place and derive merge targets from it.
cat > build-matrix.json <<'JSON'
[
{ "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-26.04" },
{ "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-26.04-arm" },
{ "tag": "cpu", "dockerfile": ".devops/s390x.Dockerfile", "platforms": "linux/s390x", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-26.04-s390x", "prebuilt_ui": true },
{ "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04" },
{ "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04-arm" },
{ "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.5.0", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04" },
{ "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.5.0", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04-arm" },
{ "tag": "musa", "dockerfile": ".devops/musa.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04" },
{ "tag": "intel", "dockerfile": ".devops/intel.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04" },
{ "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-26.04" },
{ "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-26.04-arm" },
{ "tag": "rocm", "dockerfile": ".devops/rocm.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-26.04" },
{ "tag": "openvino", "dockerfile": ".devops/openvino.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-26.04" }
{ "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" },
{ "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "cpu", "dockerfile": ".devops/s390x.Dockerfile", "platforms": "linux/s390x", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-s390x", "prebuilt_ui": true },
{ "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.3.0", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.3.0", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "musa", "dockerfile": ".devops/musa.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "intel", "dockerfile": ".devops/intel.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" },
{ "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-arm" },
{ "tag": "rocm", "dockerfile": ".devops/rocm.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
{ "tag": "openvino", "dockerfile": ".devops/openvino.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" }
]
JSON
@@ -160,11 +145,6 @@ jobs:
needs: [prepare_matrices, create_tag, build_ui]
runs-on: ${{ matrix.config.runs_on }}
# cache-mode: write # for QEMU
permissions:
actions: write
contents: read
packages: write
strategy:
fail-fast: false
matrix:
@@ -181,14 +161,14 @@ jobs:
if: ${{ matrix.config.prebuilt_ui == true }}
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
with:
name: llama-ui.zip
path: ui/apps/chat/dist
name: ui-build
path: tools/ui/dist
# - name: Set up QEMU
# if: ${{ contains(matrix.config.platforms, 'linux/amd64') }}
# uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4
# with:
# image: tonistiigi/binfmt:qemu-v10.2.1
- name: Set up QEMU
if: ${{ contains(matrix.config.platforms, 'linux/amd64') }}
uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4
with:
image: tonistiigi/binfmt:qemu-v10.2.1
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4
@@ -412,12 +392,7 @@ jobs:
merge_arch_tags:
name: Create shared tags from digests
needs: [prepare_matrices, push_to_registry, create_tag]
runs-on: ubuntu-26.04
permissions:
contents: read
packages: write
id-token: write
attestations: write
runs-on: ubuntu-24.04
strategy:
fail-fast: false
matrix:
@@ -452,7 +427,6 @@ jobs:
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create tags from digests
id: create_tags
shell: bash
run: |
set -euo pipefail
@@ -464,7 +438,6 @@ jobs:
SRC_TAG="${{ needs.create_tag.outputs.source_tag }}"
BUILD_DATE="${{ steps.build_date.outputs.date }}"
COMMIT_SHA="${{ steps.checkout.outputs.commit }}"
echo "image_repo=${IMAGE_REPO}" >> "$GITHUB_OUTPUT"
TAGS="${{ matrix.config.tag }}"
ARCHES="${{ matrix.config.arches }}"
DIGEST_GLOB="/tmp/digests/*.tsv"
@@ -531,16 +504,6 @@ jobs:
echo "Creating ${merged_versioned_tag} from ${refs[*]}"
docker buildx imagetools create "${annotations[@]}" --tag "${merged_versioned_tag}" "${refs[@]}"
if [[ "$tag_name" == "${TAGS%% *}" ]]; then
local digest
digest="$(docker buildx imagetools inspect "${merged_versioned_tag}" --format '{{.Manifest.Digest}}')"
if [[ ! "$digest" =~ ^sha256:[0-9a-f]{64}$ ]]; then
echo "Invalid digest for ${merged_versioned_tag}: ${digest}" >&2
exit 1
fi
echo "${image_type}_digest=${digest}" >> "$GITHUB_OUTPUT"
fi
}
for tag in $TAGS; do
@@ -564,24 +527,3 @@ jobs:
done
env:
GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
- name: Attest full image
if: ${{ matrix.config.full }}
uses: actions/attest@v4
with:
subject-name: ${{ steps.create_tags.outputs.image_repo }}
subject-digest: ${{ steps.create_tags.outputs.full_digest }}
- name: Attest light image
if: ${{ matrix.config.light }}
uses: actions/attest@v4
with:
subject-name: ${{ steps.create_tags.outputs.image_repo }}
subject-digest: ${{ steps.create_tags.outputs.light_digest }}
- name: Attest server image
if: ${{ matrix.config.server }}
uses: actions/attest@v4
with:
subject-name: ${{ steps.create_tags.outputs.image_repo }}
subject-digest: ${{ steps.create_tags.outputs.server_digest }}
+1 -5
View File
@@ -9,17 +9,13 @@ on:
branches:
- master
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
editorconfig:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast]
steps:
- uses: actions/checkout@v6
- uses: editorconfig-checker/action-editorconfig-checker@840e866d93b8e032123c23bac69dece044d4d84c # v2.2.0
+1 -4
View File
@@ -17,14 +17,11 @@ on:
tags:
- 'gguf-v*' # Push events to every version tag
cache-mode: none
permissions:
contents: read
jobs:
deploy:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
+4 -28
View File
@@ -25,10 +25,6 @@ on:
'scripts/hip/gcn-cdna-vgpr-check.py'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
@@ -53,22 +49,14 @@ jobs:
id: depends
run: |
sudo apt-get update
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev python3 python3-venv python3-pip jq
sudo apt-get install -y build-essential git cmake rocblas-dev hipblas-dev libssl-dev python3
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: hip-quality-check-ubuntu-22.04
folder: llama.cpp
hf_bucket: ggml-org/cache
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build with Werror
id: cmake_build
@@ -96,15 +84,3 @@ jobs:
cd build
make -j $(nproc) 2>&1 | tee metrics.log | grep -v 'Rpass-analysis=kernel-resource-usage\|remark:\|^$'
python3 ../scripts/hip/gcn-cdna-vgpr-check.py metrics.log
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: hip-quality-check-ubuntu-22.04
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
-4
View File
@@ -2,10 +2,6 @@ name: "Pull Request Labeler"
on:
- pull_request_target
cache-mode: none
permissions:
contents: read
jobs:
labeler:
permissions:
+1 -141
View File
@@ -3,74 +3,33 @@ name: Make Release
on:
workflow_dispatch:
inputs:
commit:
description: 'Commit SHA to release (empty = branch HEAD)'
required: false
default: ''
type: string
dry_run:
description: 'Dry run - validate without creating the tag'
required: true
type: boolean
default: true
skip_apiabi_check:
description: 'Skip API/ABI compatibility check'
required: false
type: boolean
default: false
require_docker:
description: 'Require the Docker workflow to have completed successfully'
required: true
type: boolean
default: true
apiabi_compare_tag:
description: 'Tag to compare against for API/ABI check (default: latest release)'
required: false
type: string
default: ''
env:
GH_TOKEN: ${{ github.token }}
cache-mode: none
permissions:
contents: write
packages: write
jobs:
make-release:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v6
with:
ssh-key: ${{ secrets.DEPLOY_KEY_RELEASE }}
ref: ${{ inputs.commit != '' && inputs.commit || github.ref_name }}
fetch-depth: 0
- name: Install API/ABI check tools
if: ${{ github.event.inputs.skip_apiabi_check != 'true' }}
run: sudo apt-get install -y abi-compliance-checker abigail-tools
- name: Run release checks
id: checks
run: bash scripts/make-release-checks.sh ${{ github.event.inputs.dry_run == 'true' && '--dry-run' || '' }}
env:
GITHUB_REPOSITORY: ${{ github.repository }}
RELEASE_BRANCH: ${{ github.ref_name }}
SKIP_APIABI_CHECK: ${{ github.event.inputs.skip_apiabi_check }}
APIABI_COMPARE_TAG: ${{ github.event.inputs.apiabi_compare_tag }}
APIABI_REPORT_DIR: ${{ runner.temp }}/apiabi-reports
REQUIRE_DOCKER: ${{ github.event.inputs.require_docker }}
- name: Upload API/ABI reports
if: ${{ always() && github.event.inputs.skip_apiabi_check != 'true' }}
uses: actions/upload-artifact@v7
with:
name: apiabi-reports
path: ${{ runner.temp }}/apiabi-reports
if-no-files-found: ignore
- name: Create release tag
if: ${{ github.event.inputs.dry_run == 'false' }}
@@ -82,111 +41,12 @@ jobs:
git push origin "${VERSION}"
echo "Created and pushed tag ${VERSION}"
- name: Generate release description
id: desc
run: bash scripts/make-release-desc.sh "${{ steps.checks.outputs.version }}"
env:
GITHUB_REPOSITORY: ${{ github.repository }}
- name: Create nightly-tag.txt
id: nightly_tag_file
run: |
NIGHTLY_TAG="${{ steps.desc.outputs.nightly_tag }}"
if [[ -z "${NIGHTLY_TAG}" ]]; then
echo "Warning: no nightly tag found for the release commit - nightly-tag.txt will not be created"
echo "create=false" >> "$GITHUB_OUTPUT"
exit 0
fi
echo "${NIGHTLY_TAG}" > nightly-tag.txt
echo "create=true" >> "$GITHUB_OUTPUT"
echo "nightly-tag.txt:"
cat nightly-tag.txt
- name: Create release
id: create_release
if: ${{ github.event.inputs.dry_run == 'false' }}
uses: ggml-org/action-create-release@v1
env:
GITHUB_TOKEN: ${{ github.token }}
with:
tag_name: ${{ steps.checks.outputs.version }}
prerelease: false
# TODO: enrich the body of the release with more information
body: |
## Overview
New version has been released.
## Assets
${{ steps.desc.outputs.nightly }}
## More info
- [Releases and versioning of `ggml-org` projects](https://github.com/ggml-org/ggml/discussions/1579)
## ${{ steps.desc.outputs.changelog_title }}
${{ steps.desc.outputs.changelog }}
- name: Upload nightly-tag.txt
if: ${{ github.event.inputs.dry_run == 'false' && steps.nightly_tag_file.outputs.create == 'true' }}
uses: actions/github-script@v8
with:
github-token: ${{secrets.GITHUB_TOKEN}}
script: |
const fs = require('fs');
const release_id = '${{ steps.create_release.outputs.id }}';
console.log('uploadReleaseAsset', 'nightly-tag.txt');
await github.rest.repos.uploadReleaseAsset({
owner: context.repo.owner,
repo: context.repo.repo,
release_id: release_id,
name: 'nightly-tag.txt',
data: await fs.readFileSync('./nightly-tag.txt')
});
- name: Re-tag container images with release version
if: ${{ github.event.inputs.dry_run == 'false' && github.event.inputs.require_docker != 'false' && steps.desc.outputs.nightly_tag != '' }}
env:
GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
run: |
VERSION="${{ steps.checks.outputs.version }}"
NIGHTLY_TAG="${{ steps.desc.outputs.nightly_tag }}"
REPO_OWNER="${GITHUB_REPOSITORY_OWNER,,}"
IMAGE_REPO="ghcr.io/${REPO_OWNER}/${{ github.event.repository.name }}"
echo "${{ secrets.GITHUB_TOKEN }}" | docker login ghcr.io -u "${{ github.actor }}" --password-stdin
VARIANTS=("" "-cuda" "-cuda13" "-vulkan" "-rocm" "-intel" "-musa" "-openvino")
TYPES=("full" "light" "server")
# the release is already created at this point, so keep going on a
# missing image and report all of them at the end
MISSING=()
for type in "${TYPES[@]}"; do
for variant in "${VARIANTS[@]}"; do
src="${IMAGE_REPO}:${type}${variant}-${NIGHTLY_TAG}"
dst="${IMAGE_REPO}:${type}${variant}-${VERSION}"
echo "Tagging ${src} -> ${dst}"
if ! docker buildx imagetools create --tag "${dst}" "${src}"; then
MISSING+=("${type}${variant}")
fi
done
done
if [[ ${#MISSING[@]} -gt 0 ]]; then
echo "::error::failed to re-tag container images for ${NIGHTLY_TAG}:${MISSING[*]}"
exit 1
fi
- name: Dry run summary
if: ${{ github.event.inputs.dry_run == 'true' }}
run: |
if [[ "${{ steps.checks.outputs.checks_passed }}" == "true" ]]; then
echo "Dry run complete - all checks passed."
echo "Would have created tag: ${{ steps.checks.outputs.version }}"
if [[ -n "${{ steps.desc.outputs.nightly_tag }}" ]]; then
echo "Would have uploaded nightly-tag.txt: ${{ steps.desc.outputs.nightly_tag }}"
fi
else
echo "::error::Dry run found release check failures. A release tag would not be created."
exit 1
-461
View File
@@ -1,461 +0,0 @@
name: Models Backend Check
on:
workflow_dispatch: # allows manual triggering
push:
branches:
- master
paths: [
'.github/workflows/models-check.yml',
'ggml/**',
'tests/fusion/**',
'tests/test-fusion.cpp',
'tests/test-llama-archs.cpp',
'src/llama-graph*',
'src/llama-kv-cache*',
'src/llama-model*',
'src/models/**'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/models-check.yml',
'ggml/**',
'tests/fusion/**',
'tests/test-fusion.cpp',
'tests/test-llama-archs.cpp',
'src/llama-graph*',
'src/llama-kv-cache*',
'src/llama-model*',
'src/models/**'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
GGML_NLOOP: 3
GGML_N_THREADS: 1
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
jobs:
cuda:
runs-on: "hf-jobs-t4-medium:cuda13"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y cmake time python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: models-check-cuda
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_OPENSSL=OFF \
-DGGML_SCHED_NO_REALLOC=ON \
-DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc \
-DGGML_CUDA=ON
time cmake --build build --config Release --target test-llama-archs -j$(nproc)
time cmake --build build --config Release --target test-fusion -j$(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: models-check-cuda
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
# - name: Generate models
# id: generate_models
# run: |
# rm -rf build-ci-models && mkdir -p build-ci-models
# ./build/bin/test-llama-archs -o build-ci-models
# TODO: add for backends as they adopt the fusion debug API
# - name: Test fusion
# id: test_fusion
# run: |
# ./build/bin/test-fusion --models build-ci-models --device CUDA0 --check tests/fusion/CUDA.csv
- name: Test archs
id: test_archs
run: |
GGML_CUDA_DEVICES=1 ./build/bin/test-llama-archs -s 1
GGML_CUDA_DEVICES=2 ./build/bin/test-llama-archs -s 1
GGML_CUDA_DEVICES=3 ./build/bin/test-llama-archs -s 1
GGML_CUDA_DEVICES=4 ./build/bin/test-llama-archs -s 1
metal:
runs-on: [self-hosted, macOS, ARM64]
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_OPENSSL=OFF \
-DGGML_SCHED_NO_REALLOC=ON \
-DGGML_BLAS=OFF \
-DGGML_METAL=ON
time cmake --build build --config Release --target test-llama-archs -j $(sysctl -n hw.logicalcpu)
time cmake --build build --config Release --target test-fusion -j $(sysctl -n hw.logicalcpu)
- name: Generate models
id: generate_models
run: |
rm -rf build-ci-models && mkdir -p build-ci-models
./build/bin/test-llama-archs -o build-ci-models
- name: Test KV shift
id: test_kv_shift
run: |
./build/bin/test-llama-archs --kv-shift
- name: Test fusion
id: test_fusion
run: |
./build/bin/test-fusion --models build-ci-models --device MTL0 --check tests/fusion/MTL.csv
- name: Test archs
id: test_archs
run: |
GGML_METAL_DEVICES=1 ./build/bin/test-llama-archs -s 1
GGML_METAL_DEVICES=2 ./build/bin/test-llama-archs -s 1
GGML_METAL_DEVICES=3 ./build/bin/test-llama-archs -s 1
GGML_METAL_DEVICES=4 ./build/bin/test-llama-archs -s 1
rocm:
runs-on: [self-hosted, Linux, gfx1201, 1accel]
container: "rocm/dev-ubuntu-24.04:7.2.4-complete"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
apt update
apt install -y build-essential jq cmake time python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: models-check-rocm
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_OPENSSL=OFF \
-DGGML_SCHED_NO_REALLOC=ON \
-DCMAKE_HIP_COMPILER=$(hipconfig -l)/clang \
-DGPU_TARGETS=gfx1201 \
-DGGML_HIP=ON
time cmake --build build --config Release --target test-llama-archs -j$(nproc)
time cmake --build build --config Release --target test-fusion -j$(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: models-check-rocm
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
# - name: Generate models
# id: generate_models
# run: |
# rm -rf build-ci-models && mkdir -p build-ci-models
# ./build/bin/test-llama-archs -o build-ci-models
# TODO: add for backends as they adopt the fusion debug API
# - name: Test fusion
# id: test_fusion
# run: |
# ./build/bin/test-fusion --models build-ci-models --device CUDA0 --check tests/fusion/CUDA.csv
- name: Test archs
id: test_archs
run: |
GGML_CUDA_DEVICES=1 ./build/bin/test-llama-archs -s 1
GGML_CUDA_DEVICES=2 ./build/bin/test-llama-archs -s 1
GGML_CUDA_DEVICES=3 ./build/bin/test-llama-archs -s 1
GGML_CUDA_DEVICES=4 ./build/bin/test-llama-archs -s 1
vulkan-nvidia:
runs-on: "hf-jobs-t4-small:ubuntu26_04"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan-dev glslc spirv-headers vulkan-tools mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 time python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: models-check-vulkan-nvidia
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_OPENSSL=OFF \
-DGGML_SCHED_NO_REALLOC=ON \
-DGGML_VULKAN=ON
time cmake --build build --config Release --target test-llama-archs -j$(nproc)
time cmake --build build --config Release --target test-fusion -j$(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: models-check-vulkan-nvidia
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
# - name: Generate models
# id: generate_models
# run: |
# rm -rf build-ci-models && mkdir -p build-ci-models
# ./build/bin/test-llama-archs -o build-ci-models
# TODO: add for backends as they adopt the fusion debug API
# - name: Test fusion
# id: test_fusion
# run: |
# ./build/bin/test-fusion --models build-ci-models --device Vulkan0 --check tests/fusion/Vulkan.csv
- name: Test KV shift
id: test_kv_shift
run: |
./build/bin/test-llama-archs --kv-shift
- name: Test archs
id: test_archs
run: |
./build/bin/test-llama-archs -s 1
vulkan-amd:
runs-on: [self-hosted, Linux, gfx1201, 1accel]
container: "ubuntu:26.04"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
apt update
apt install -y build-essential jq cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan-dev glslc spirv-headers vulkan-tools mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 time python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: models-check-vulkan-amd
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_OPENSSL=OFF \
-DGGML_SCHED_NO_REALLOC=ON \
-DGGML_VULKAN=ON
time cmake --build build --config Release --target test-llama-archs -j$(nproc)
time cmake --build build --config Release --target test-fusion -j$(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: models-check-vulkan-amd
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
# - name: Generate models
# id: generate_models
# run: |
# rm -rf build-ci-models && mkdir -p build-ci-models
# ./build/bin/test-llama-archs -o build-ci-models
# TODO: add for backends as they adopt the fusion debug API
# - name: Test fusion
# id: test_fusion
# run: |
# ./build/bin/test-fusion --models build-ci-models --device Vulkan0 --check tests/fusion/Vulkan.csv
- name: Test archs
id: test_archs
run: |
./build/bin/test-llama-archs -s 1
webgpu-nvidia:
runs-on: "hf-jobs-t4-small:ubuntu26_04"
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y build-essential cmake libxcb-xinput0 libxcb-xinerama0 libxcb-cursor-dev libvulkan1 mesa-vulkan-drivers libglvnd0 libgl1 libglx0 libegl1 libgles2 time python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: models-check-webgpu-nvidia
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Dawn Dependency
id: dawn-depends
run: |
DAWN_VERSION="v20260908.214631"
DAWN_OWNER="google"
DAWN_REPO="dawn"
DAWN_ASSET_NAME="Dawn-94c3c9cc0d5fb2e85aebb370fa8d37b71aa34655-ubuntu-latest-Release"
echo "Fetching release asset from https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
curl -L -o artifact.tar.gz \
"https://github.com/google/dawn/releases/download/${DAWN_VERSION}/${DAWN_ASSET_NAME}.tar.gz"
mkdir dawn
tar -xvf artifact.tar.gz -C dawn --strip-components=1
- name: Build
id: cmake_build
run: |
cmake -B build \
-DCMAKE_BUILD_TYPE=Release \
-DLLAMA_FATAL_WARNINGS=ON \
-DLLAMA_OPENSSL=OFF \
-DGGML_SCHED_NO_REALLOC=ON \
-DCMAKE_PREFIX_PATH="$GITHUB_WORKSPACE/dawn" \
-DDawn_DIR="$GITHUB_WORKSPACE/dawn/lib64/cmake/Dawn" \
-DGGML_WEBGPU=ON
time cmake --build build --config Release --target test-llama-archs -j$(nproc)
time cmake --build build --config Release --target test-fusion -j$(nproc)
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: models-check-webgpu-nvidia
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
# - name: Generate models
# id: generate_models
# run: |
# rm -rf build-ci-models && mkdir -p build-ci-models
# ./build/bin/test-llama-archs -o build-ci-models
# TODO: add for backends as they adopt the fusion debug API
# - name: Test fusion
# id: test_fusion
# run: |
# ./build/bin/test-fusion --models build-ci-models --device WebGPU --check tests/fusion/WebGPU.csv
- name: Test archs
id: test_archs
run: |
./build/bin/test-llama-archs -s 1
-1
View File
@@ -4,7 +4,6 @@ on:
pull_request_target:
types: [labeled]
cache-mode: none
permissions:
pull-requests: write
issues: write
-37
View File
@@ -1,37 +0,0 @@
name: "PR video demo label"
on:
pull_request_target:
types: [opened, edited, reopened, synchronize]
cache-mode: none
permissions:
pull-requests: write
issues: write
jobs:
video-demo-label:
runs-on: ubuntu-slim
steps:
- name: Add or remove the video demo label
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
PR_URL: ${{ github.event.pull_request.html_url }}
PR_NUMBER: ${{ github.event.pull_request.number }}
# passed through env, so the body is only matched, never run, and is safe to read from a fork
BODY: ${{ github.event.pull_request.body }}
HAS_LABEL: ${{ contains(github.event.pull_request.labels.*.name, 'video demo') }}
run: |
# sections written by demo:pr (see ui/apps/chat/demo/cli.ts): the managed comment
# markers, or a preview linking to a demo video uploaded for this PR
has_demo=false
if { grep -qF '<!-- demo:start -->' <<< "$BODY" && grep -qF '<!-- demo:end -->' <<< "$BODY"; } ||
grep -qE "/resolve/videos/pr/$PR_NUMBER/[0-9a-f]{10}(-[0-9]+)?\.mp4" <<< "$BODY"; then
has_demo=true
fi
if [ "$has_demo" = true ] && [ "$HAS_LABEL" = false ]; then
gh pr edit "$PR_URL" --add-label 'video demo'
elif [ "$has_demo" = false ] && [ "$HAS_LABEL" = true ]; then
gh pr edit "$PR_URL" --remove-label 'video demo'
fi
+1 -5
View File
@@ -10,13 +10,9 @@ on:
- 'conversion/base.py'
- 'convert_hf_to_gguf_update.py'
cache-mode: none
permissions:
contents: read
jobs:
pre-tokenizer-hashes:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast]
steps:
- name: Checkout repository
@@ -14,17 +14,13 @@ on:
- 'convert*.py'
- '**/requirements*.txt'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
python-check-requirements:
runs-on: ${{ 'ubuntu-26.04-arm' || 'ubuntu-26.04' }}
runs-on: [self-hosted, CPU, fast]
name: check-requirements
steps:
- name: Check out source repository
+1 -5
View File
@@ -15,17 +15,13 @@ on:
'**/*.py'
]
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
flake8-lint:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast]
name: Lint
steps:
- name: Check out source repository
+3 -7
View File
@@ -16,17 +16,13 @@ on:
- '**/requirements*.txt'
# - 'pyrightconfig.json'
cache-mode: none
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
jobs:
python-type-check:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast]
name: python type-check
steps:
- name: Check out source repository
@@ -35,7 +31,7 @@ jobs:
uses: actions/setup-python@v6
with:
python-version: "3.11"
pip-install: -r requirements/requirements-all.txt ty==0.0.100
pip-install: -r requirements/requirements-all.txt ty==0.0.35
# - name: Type-check with Pyright
# uses: jakebailey/pyright-action@v2
# with:
@@ -44,4 +40,4 @@ jobs:
# warnings: true
- name: Type-check with ty
run: |
ty check --exit-zero-on-warning --output-format=github
ty check --output-format=github
-249
View File
@@ -1,249 +0,0 @@
name: Publish Release
on:
workflow_run:
workflows:
- Release
types:
- completed
branches:
- master
run-name: "Publish ${{ github.event.workflow_run.display_title }}"
cache-mode: none
permissions:
actions: read
contents: read
env:
GH_TOKEN: ${{ github.token }}
BRANCH_NAME: master
jobs:
publish:
if: ${{ github.event.workflow_run.conclusion == 'success' }}
# Fine-grained permission
# https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
permissions:
actions: read
contents: write # for creating release
id-token: write
attestations: write
runs-on: ubuntu-latest
outputs:
should_release: ${{ steps.check.outputs.should_release }}
tag_name: ${{ steps.tag.outputs.name }}
steps:
- id: check
env:
COMMIT_MESSAGE: ${{ github.event.workflow_run.head_commit.message }}
run: |
if echo "$COMMIT_MESSAGE" | grep -q '\[no release\]'; then
echo "should_release=false" >> $GITHUB_OUTPUT
else
echo "should_release=true" >> $GITHUB_OUTPUT
fi
- name: Clone
if: ${{ steps.check.outputs.should_release == 'true' }}
id: checkout
uses: actions/checkout@v6
with:
ref: ${{ github.event.workflow_run.head_sha }}
fetch-depth: 0
ssh-key: ${{ secrets.DEPLOY_KEY_RELEASE }}
- name: Determine tag name
if: ${{ steps.check.outputs.should_release == 'true' }}
id: tag
uses: ./.github/actions/get-tag-name
- name: Download artifacts
if: ${{ steps.check.outputs.should_release == 'true' }}
id: download-artifact
uses: actions/download-artifact@v8
with:
path: ./artifact
run-id: ${{ github.event.workflow_run.id }}
github-token: ${{ github.token }}
merge-multiple: true
skip-decompress: true
- name: Merge artifacts
if: ${{ steps.check.outputs.should_release == 'true' }}
id: move_artifacts
run: |
mkdir -p release
# the windows-cpu zip contains the full toolset (llama-server with the embedded
# UI, ggml-cpu) - inject it into the other windows zips so that every archive
# ships the same binaries, only with a different backend library on top
echo "Injecting windows-cpu binaries (llama-server + CPU backend) into the backend zips..."
for arch in x64 arm64; do
cpu_zip="artifact/llama-bin-win-cpu-${arch}.zip"
temp_dir=$(mktemp -d)
echo "Extracting windows-cpu-${arch} package..."
unzip "$cpu_zip" -d "$temp_dir"
echo "Merging into $arch zips..."
for target_zip in artifact/llama-bin-win-*-${arch}.zip; do
if [[ "$target_zip" == "$cpu_zip" ]]; then
continue
fi
echo "Injecting into $(basename "$target_zip")"
realpath_target_zip=$(realpath "$target_zip")
(cd "$temp_dir" && zip -r "$realpath_target_zip" .)
done
rm -rf "$temp_dir"
done
echo "Renaming and moving zips to release..."
for zip_file in artifact/llama-bin-win-*.zip; do
base_name=$(basename "$zip_file" .zip)
zip_name="llama-${{ steps.tag.outputs.name }}-${base_name#llama-}.zip"
echo "Moving $zip_file to release/$zip_name"
mv "$zip_file" "release/$zip_name"
done
echo "Moving other artifacts..."
rm -f artifact/llama-ui.zip
mv -v artifact/*.zip release
mv -v artifact/*.tar.gz release
- name: Download UI build
if: ${{ steps.check.outputs.should_release == 'true' }}
id: download_ui
uses: actions/download-artifact@v8
with:
name: llama-ui.zip
path: ./ui-dist
run-id: ${{ github.event.workflow_run.id }}
github-token: ${{ github.token }}
- name: Package UI
if: ${{ steps.check.outputs.should_release == 'true' }}
id: package_ui
run: |
tar -czvf release/llama-${{ steps.tag.outputs.name }}-ui.tar.gz --transform "s,^\.,llama-${{ steps.tag.outputs.name }}," -C ./ui-dist .
- name: Attest release artifacts
if: ${{ steps.check.outputs.should_release == 'true' }}
id: attest
uses: actions/attest@v4
with:
subject-path: 'release/*'
- name: Create release
if: ${{ steps.check.outputs.should_release == 'true' }}
id: create_release
uses: ggml-org/action-create-release@v1
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
tag_name: ${{ steps.tag.outputs.name }}
commitish: ${{ github.event.workflow_run.head_sha }}
prerelease: true
body: |
<details open>
${{ github.event.workflow_run.head_commit.message }}
</details>
**Website:**
- <https://llama.app>
**Attestations:**
- <${{ steps.attest.outputs.attestation-url }}>
**macOS/iOS:**
- [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz)
- macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780)
- [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz)
- [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-xcframework.zip)
**Linux:**
- [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.tar.gz)
- [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-arm64.tar.gz)
- [Ubuntu 24.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-s390x.tar.gz)
- [Ubuntu 26.04 s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-26.04-s390x.tar.gz)
- [Ubuntu 26.04 s390x (zDNN)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-zdnn-s390x.tar.gz)
- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.tar.gz)
- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-arm64.tar.gz)
- [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz)
- [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.5-x64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.5-x64.tar.gz)
- [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.5-arm64.tar.gz) - [CUDA 13.5 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.5-arm64.tar.gz)
- [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-10.0-x64.tar.gz)
- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-2026.4.1-x64.tar.gz)
- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp32-x64.tar.gz)
- [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp16-x64.tar.gz)
- [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-linux-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md)
**Android:**
- [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz)
- [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-android-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md)
**Windows:**
- [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cpu-x64.zip)
- [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cpu-arm64.zip)
- [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-opencl-adreno-arm64.zip)
- [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-bin-win-cuda-12.4-x64.zip)
- [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cuda-13.5-x64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-bin-win-cuda-13.5-x64.zip)
- [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cuda-13.5-arm64.zip) - [CUDA 13.5 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-bin-win-cuda-13.5-arm64.zip)
- [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-vulkan-x64.zip)
- [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-vulkan-arm64.zip)
- [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-openvino-2026.4.1-x64.zip)
- [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip)
- [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-rocm-10.0-x64.zip)
**openEuler:**
- [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705)
- openEuler x86 (310p)
- openEuler x86 (910b, ACL Graph)
- openEuler aarch64 (310p)
- openEuler aarch64 (910b, ACL Graph)
**UI:**
- [UI](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-ui.tar.gz)
- name: Upload release
if: ${{ steps.check.outputs.should_release == 'true' }}
id: upload_release
uses: actions/github-script@v8
with:
github-token: ${{secrets.GITHUB_TOKEN}}
script: |
const path = require('path');
const fs = require('fs');
const release_id = '${{ steps.create_release.outputs.id }}';
for (let file of await fs.readdirSync('./release')) {
if (path.extname(file) === '.zip' || file.endsWith('.tar.gz')) {
console.log('uploadReleaseAsset', file);
await github.rest.repos.uploadReleaseAsset({
owner: context.repo.owner,
repo: context.repo.repo,
release_id: release_id,
name: file,
data: await fs.readFileSync(`./release/${file}`)
});
}
}
ui-publish:
if: ${{ needs.publish.outputs.should_release == 'true' }}
needs:
- publish
uses: ./.github/workflows/ui-publish.yml
with:
version_tag: ${{ needs.publish.outputs.tag_name }}
run_id: ${{ github.event.workflow_run.id }}
secrets:
hf_token: ${{ secrets.HF_TOKEN_UI_STATIC_OUTPUT }}
File diff suppressed because it is too large Load Diff
+27 -36
View File
@@ -31,13 +31,7 @@ on:
'.github/workflows/server-sanitize.yml'
]
cache-mode: none
permissions:
contents: read
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
@@ -49,7 +43,7 @@ concurrency:
jobs:
server:
runs-on: hf-jobs-cpu-performance
runs-on: [self-hosted, CPU, Linux, llama-server]
strategy:
matrix:
@@ -58,6 +52,20 @@ jobs:
fail-fast: false
steps:
#- name: Dependencies
# id: depends
# run: |
# sudo apt-get update
# sudo apt-get -y install \
# build-essential \
# xxd \
# git \
# cmake \
# curl \
# wget \
# language-pack-en \
# libssl-dev
- name: Clone
id: checkout
uses: actions/checkout@v6
@@ -65,23 +73,12 @@ jobs:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y build-essential cmake python3-full
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
- name: Setup Node.js
uses: actions/setup-node@v6
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: server-sanitize-${{ matrix.sanitizer }}
folder: llama.cpp
hf_bucket: ggml-org/cache
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Build
id: cmake_build
@@ -97,17 +94,9 @@ jobs:
-DLLAMA_SANITIZE_UNDEFINED=${{ matrix.sanitizer == 'UNDEFINED' }}
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: server-sanitize-${{ matrix.sanitizer }}
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Python setup
id: setup_python
uses: actions/setup-python@v7
- name: Install Python dependencies
run: |
@@ -120,7 +109,8 @@ jobs:
run: |
source .venv/bin/activate
cd tools/server/tests
PYTEST_WORKERS=4 ./tests.sh
export ${{ matrix.extra_args }}
./tests.sh
- name: Slow tests
id: server_integration_tests_slow
@@ -128,4 +118,5 @@ jobs:
run: |
source .venv/bin/activate
cd tools/server/tests
PYTEST_WORKERS=4 SLOW_TESTS=1 ./tests.sh
export ${{ matrix.extra_args }}
SLOW_TESTS=1 ./tests.sh
+12 -46
View File
@@ -28,10 +28,6 @@ on:
'tools/server/**.*'
]
cache-mode: none
permissions:
contents: read
env:
# note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
@@ -76,7 +72,7 @@ jobs:
run: |
cd tools/server/tests
source venv/bin/activate
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
@@ -85,7 +81,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
- name: Tests (GPUx2)
id: server_integration_tests_gpu2
@@ -94,7 +90,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
- name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling
@@ -103,10 +99,10 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
server-cuda:
runs-on: "hf-jobs-t4-medium:cuda13"
runs-on: [self-hosted, llama-server, Linux, NVIDIA]
steps:
- name: Clone
@@ -116,42 +112,12 @@ jobs:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Install dependencies
run: |
sudo apt update
sudo apt install -y cmake libssl-dev python3 python3-venv python3-pip
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
with:
key: self-hosted-server-cuda
folder: llama.cpp
hf_bucket: ggml-org/cache
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc
cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: self-hosted-server-cuda
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Python setup
id: setup_python
run: |
@@ -166,7 +132,7 @@ jobs:
run: |
cd tools/server/tests
source venv/bin/activate
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
@@ -175,7 +141,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
- name: Tests (GPUx2)
id: server_integration_tests_gpu2
@@ -184,7 +150,7 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_CUDA_DEVICES=2
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
- name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling
@@ -193,10 +159,10 @@ jobs:
cd tools/server/tests
source venv/bin/activate
export GGML_CUDA_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
PYTEST_WORKERS=1 ./tests.sh
./tests.sh
server-kleidiai:
runs-on: ah-ubuntu_24_04-c8g_8x
runs-on: ah-ubuntu_22_04-c8g_8x
steps:
- name: Clone
@@ -236,7 +202,7 @@ jobs:
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON -DLLAMA_FATAL_WARNINGS=ON
cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Python setup
-100
View File
@@ -1,100 +0,0 @@
name: Server (speculative decoding)
on:
workflow_dispatch:
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
spec_methods:
description: 'Speculative methods to test'
required: true
default: 'compact'
type: choice
options:
- compact
- nightly
- all
push:
branches:
- master
paths: [
'.github/workflows/server-speculative.yml',
'common/speculative.*',
'src/models/dflash*.cpp',
'src/models/dspark.cpp',
'src/models/eagle3.cpp',
'src/models/lilicorr.cpp',
'src/models/qwen35.cpp',
'tools/server/tests/unit/test_spec_methods.py'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/server-speculative.yml',
'common/speculative.*',
'src/models/dflash*.cpp',
'src/models/dspark.cpp',
'src/models/eagle3.cpp',
'src/models/lilicorr.cpp',
'src/models/qwen35.cpp',
'tools/server/tests/unit/test_spec_methods.py'
]
cache-mode: none
permissions:
contents: read
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
server-speculative:
runs-on: [self-hosted, Linux, gb10, perf]
container: "nvidia/cuda:13.4.3-devel-ubuntu26.04"
timeout-minutes: 60
defaults:
run:
shell: bash
steps:
- name: Clone
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Install dependencies
run: |
apt update
apt install -y cmake libssl-dev python3 python3-venv python3-pip
- name: Build
run: |
cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Python setup
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- name: Test speculative decoding
env:
SPEC_METHODS: ${{ github.event.inputs.spec_methods || 'compact' }}
# pull requests from forks do not get repository variables
SPEC_MODEL_DIR: ${{ vars.SPEC_METHOD_MODEL_DIR || '/mnt/cache/spec-models' }}
N_GPU_LAYERS: 99
run: |
cd tools/server/tests
source venv/bin/activate
PYTEST_WORKERS=1 ./tests.sh -s -v unit/test_spec_methods.py
+6 -45
View File
@@ -43,10 +43,6 @@ on:
'tools/server/**.*'
]
cache-mode: none
permissions:
contents: read
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
@@ -59,7 +55,7 @@ concurrency:
jobs:
ubuntu:
runs-on: ubuntu-26.04-arm
runs-on: ubuntu-24.04-arm
steps:
- name: Dependencies
@@ -84,19 +80,11 @@ jobs:
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
restore: false
save: false
- name: ccache-buckets-restore
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}
with:
key: server-ubuntu-26.04-arm
folder: llama.cpp
hf_bucket: ggml-org/cache
key: server-ubuntu-24.04-arm
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
@@ -105,18 +93,6 @@ jobs:
-DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: ccache-buckets-save
if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
uses: ./.github/actions/ccache-buckets
env:
HF_TOKEN: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }}
with:
key: server-ubuntu-26.04-arm
folder: llama.cpp
evict-old-files: 1d
hf_bucket: ggml-org/cache
save: true
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
@@ -155,11 +131,6 @@ jobs:
windows:
runs-on: windows-2025
cache-mode: write
permissions:
actions: write
contents: read
steps:
- name: Clone
id: checkout
@@ -169,7 +140,7 @@ jobs:
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.24
uses: ggml-org/ccache-action@v1.2.21
with:
key: server-windows-2025-x64
evict-old-files: 1d
@@ -210,13 +181,3 @@ jobs:
cd tools/server/tests
export SLOW_TESTS="1"
./tests.sh
- name: ccache-clear
uses: ./.github/actions/ccache-clear
env:
GH_TOKEN: ${{ github.token }}
with:
key: server-windows-2025-x64
older: 5m
min: 1
dry-run: ${{ github.event_name != 'push' || github.ref != 'refs/heads/master' }}
+6 -12
View File
@@ -3,11 +3,6 @@ name: UI Build (self-hosted)
on:
workflow_call:
cache-mode: none
permissions:
actions: write
contents: read
jobs:
build:
runs-on: [self-hosted, fast]
@@ -22,21 +17,20 @@ jobs:
uses: actions/setup-node@v6
with:
node-version: "24"
# cache: "npm"
# cache-dependency-path: "ui/apps/chat/package-lock.json"
package-manager-cache: false
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install dependencies
run: npm ci
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Build application
run: npm run build
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Upload built UI
uses: actions/upload-artifact@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
name: ui-build
path: tools/ui/dist/
retention-days: 1
+15 -29
View File
@@ -3,60 +3,46 @@ name: UI Build
on:
workflow_call:
inputs:
ui_version:
description: 'Version string embedded in build.json (e.g. b1234); defaults to b<commit-count>'
hf_ui_version:
description: 'Version string for version.json (e.g. 12345)'
required: false
type: string
cache-mode: none
permissions:
actions: write
contents: read
jobs:
build:
runs-on: ubuntu-26.04-arm
runs-on: ubuntu-slim
env:
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Resolve UI version
id: version
run: |
version="${{ inputs.ui_version }}"
if [ -z "$version" ]; then
version="b$(git rev-list --count HEAD)"
fi
echo "ui_version=${version}" >> $GITHUB_OUTPUT
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
# cache: "npm"
# cache-dependency-path: "ui/apps/chat/package-lock.json"
package-manager-cache: false
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install dependencies
run: npm ci
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Build application
env:
LLAMA_BUILD_NUMBER: ${{ steps.version.outputs.ui_version }}
HF_UI_VERSION: ${{ inputs.hf_ui_version || '' }}
LLAMA_BUILD_NUMBER: ${{ inputs.hf_ui_version || 'b0000' }}
run: npm run build
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run PWA unit tests (versioned build output)
run: npx vitest --project=unit --run tests/unit/pwa.spec.ts
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Upload built UI
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
name: ui-build
path: tools/ui/dist/
retention-days: 1
-201
View File
@@ -1,201 +0,0 @@
name: UI Lib Publish
# Publishes @ggml-org/llama-ui, the library in ui/lib/ui, to npm.
#
# The version in ui/lib/ui/package.json is the release. A commit that reaches master with a
# version npm does not have builds the library and publishes it; a commit that changes the
# library without bumping it publishes nothing and says so on the run, which is the drift that
# let 0.3.0 sit a day behind master. Bump the version in the PR whose change should ship, and
# this workflow does the rest.
#
# Auth: no npm token is stored here. The job exchanges its OIDC identity for one (npm trusted
# publishing) and signs the tarball with a provenance attestation. release-publish.yml has done
# the same exchange on every push to master since it landed, its actions/attest step being the
# proof that this repository can be issued a token.
#
# One-time setup, before this can publish: on the package, Publishing settings, Trusted
# Publisher, GitHub Actions, with organization ggml-org, repository llama.cpp, workflow file
# ui-lib-publish.yml, and Environment left blank - this job names no environment, since creating
# one needs repository admin. Merging this workflow before that exists leaves the publish step
# red on master: the release is late rather than wrong, and re-running the job publishes it.
on:
workflow_dispatch:
inputs:
dry_run:
description: 'Build and pack, but do not publish'
required: false
type: boolean
default: false
push:
branches:
- master
paths: [
'.github/workflows/ui-lib-publish.yml',
'ui/lib/ui/**.*'
]
# the advisory half, so a library change without a bump is annotated on the PR rather than
# discovered after the merge: the path filter keeps it off PRs that touch only Llama Chat
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/ui-lib-publish.yml',
'ui/lib/ui/**.*'
]
cache-mode: none
permissions:
contents: read
id-token: write
concurrency:
# never cancel a run mid-publish: a version half-published cannot be taken back. GitHub holds
# one pending run per group, so a newer push replaces an older queued one - no release is lost,
# as each run reads the version from its own commit.
group: ${{ github.workflow }}
cancel-in-progress: false
env:
LIB_DIR: ui/lib/ui
jobs:
publish:
name: Publish @ggml-org/llama-ui
if: github.repository == 'ggml-org/llama.cpp'
runs-on: ubuntu-26.04-arm
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
registry-url: 'https://registry.npmjs.org'
package-manager-cache: false
- name: Check npm can publish with an OIDC token
run: |
npm -v
node -e '
const v = process.argv[1];
const [major, minor] = v.split(".").map(Number);
if (major < 11 || (major === 11 && minor < 5)) {
console.error(`npm ${v} cannot publish with trusted publishing: 11.5.1 or newer is needed`);
process.exit(1);
}
' "$(npm -v)"
- name: Install dependencies
run: npm ci
working-directory: ${{ env.LIB_DIR }}
- name: Run type checking
run: npm run check
working-directory: ${{ env.LIB_DIR }}
- name: Build the package and lint it
run: npm run prepack
working-directory: ${{ env.LIB_DIR }}
- name: Compare the version with npm
id: version
# on a PR this is advisory and must not fail the job: a registry outage is not the
# contributor's mistake. On master the publish decision rests on the answer, so it fails.
continue-on-error: ${{ github.event_name == 'pull_request' }}
run: node scripts/npm-version-check.mjs
working-directory: ${{ env.LIB_DIR }}
- name: Note a library change that ships no new version
if: github.event_name == 'pull_request' && always() && steps.version.outcome == 'success' && steps.version.outputs.should_publish != 'true'
env:
NOTE: ${{ steps.version.outputs.note }}
run: echo "::warning::$NOTE"
- name: Publish
# master only. npm's trusted publisher matches on the repository and the workflow file,
# not the branch, so this condition is the only thing stopping a manual run from a PR
# branch - one that anyone with write access can start - from publishing code that no
# one reviewed. A dispatch on master remains the way to re-run a release.
if: github.ref == 'refs/heads/master' && steps.version.outputs.should_publish == 'true' && inputs.dry_run != true
# --ignore-scripts publishes the tarball prepack built and publint passed rather than
# rebuilding it here; --provenance is implied by trusted publishing and named to be
# explicit. A package published with nothing in it cannot be taken back, so refuse first.
env:
TAG: ${{ steps.version.outputs.tag }}
run: |
test -d dist || { echo "dist/ is missing: nothing was built, so nothing is published"; exit 1; }
npm publish --access public --provenance --ignore-scripts --tag "$TAG"
working-directory: ${{ env.LIB_DIR }}
- name: Verify it landed
if: github.ref == 'refs/heads/master' && steps.version.outputs.should_publish == 'true' && inputs.dry_run != true
env:
NAME: ${{ steps.version.outputs.name }}
VERSION: ${{ steps.version.outputs.version }}
run: |
# the registry can serve a new version some time after publish returns, so retry rather
# than call a release that worked a failure
for try in 1 2 3 4 5 6; do
seen=$(npm view "$NAME@$VERSION" version 2>/dev/null || true)
if [ "$seen" = "$VERSION" ]; then
echo "$NAME@$VERSION is on npm"
npm view "$NAME@$VERSION" dist-tags version dist.integrity
exit 0
fi
echo "not visible yet (attempt $try of 6)"
sleep 10
done
echo "::error::$NAME@$VERSION published without error but is not visible on the registry after 6 attempts. The publish did not fail: check the package on npm before publishing again."
exit 1
- name: Report
if: always()
# every value reaches the shell through env, not through the script, so a package name
# from a PR's package.json cannot inject into this step
env:
NAME: ${{ steps.version.outputs.name || '@ggml-org/llama-ui' }}
VERSION: ${{ steps.version.outputs.version || 'unknown' }}
LATEST: ${{ steps.version.outputs.latest }}
VERDICT: ${{ steps.version.outputs.verdict || 'not reached' }}
NOTE: ${{ steps.version.outputs.note }}
SHOULD: ${{ steps.version.outputs.should_publish }}
DRY: ${{ inputs.dry_run }}
run: |
if [ "$DRY" = "true" ]; then published="no (dry run)"
elif [ "$SHOULD" = "true" ]; then published=yes
else published=no
fi
{
echo "### $NAME $VERSION"
echo
echo "| | |"
echo "| --- | --- |"
echo "| npm latest was | ${LATEST:-nothing published yet} |"
echo "| verdict | \`$VERDICT\` |"
echo "| published | $published |"
echo
echo "> $NOTE"
} >> "$GITHUB_STEP_SUMMARY"
- name: Mind the verdict
if: always() && github.event_name != 'pull_request' && steps.version.outcome == 'success'
# a version going backwards is a mistake; a version not bumped is usually one too, but it
# is also what a stories-only commit looks like, so that only fails the run when the
# repository variable UI_LIB_PUBLISH_FAIL_ON_UNBUMPED is set to true
env:
NOTE: ${{ steps.version.outputs.note }}
VERDICT: ${{ steps.version.outputs.verdict }}
FAIL_ON_UNBUMPED: ${{ vars.UI_LIB_PUBLISH_FAIL_ON_UNBUMPED }}
run: |
case "$VERDICT" in
stale)
echo "::error::$NOTE"
exit 1 ;;
published)
if [ "$FAIL_ON_UNBUMPED" = "true" ]; then
echo "::error::$NOTE"
exit 1
fi
echo "::warning::$NOTE" ;;
esac
+21 -18
View File
@@ -7,41 +7,44 @@ on:
description: 'Version tag to publish under (e.g., b1234)'
required: true
type: string
run_id:
required: true
type: number
secrets:
hf_token:
description: 'Hugging Face token with write access'
required: true
cache-mode: none
permissions:
actions: read
contents: read
jobs:
build:
name: Build static output
uses: ./.github/workflows/ui-build.yml
publish:
name: Publish UI Static Output
needs: build
runs-on: ubuntu-slim
permissions:
contents: read
env:
HF_BUCKET_NAME: ${{ vars.HF_BUCKET_UI_STATIC_OUTPUT }}
steps:
- name: Download UI build artifact
uses: actions/download-artifact@v8
- name: Checkout code
uses: actions/checkout@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
run-id: ${{ inputs.run_id }}
github-token: ${{ github.token }}
fetch-depth: 1
- name: Download UI build artifact
uses: actions/download-artifact@v7
with:
name: ui-build
path: tools/ui/dist/
- name: Create distribution archive
run: |
tar -czf dist.tar.gz -C ui/apps/chat/dist .
tar -czf dist.tar.gz -C tools/ui/dist .
sha256sum dist.tar.gz > dist.tar.gz.sha256
mv dist.tar.gz dist.tar.gz.sha256 ui/apps/chat/dist/
mv dist.tar.gz dist.tar.gz.sha256 tools/ui/dist/
- name: Install Hugging Face Hub CLI
run: pip install -U huggingface_hub
@@ -52,12 +55,12 @@ jobs:
- name: Sync built files to Hugging Face bucket (version tag)
run: |
# Upload the built files to the Hugging Face bucket under the release version
hf buckets sync ui/apps/chat/dist hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/${{ inputs.version_tag }} --delete --quiet
hf buckets sync tools/ui/dist hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/${{ inputs.version_tag }} --delete --quiet
- name: Sync built files to Hugging Face bucket (latest)
run: |
# Also upload to the 'latest' directory for fallback downloads
hf buckets sync ui/apps/chat/dist hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/latest --delete --quiet
hf buckets sync tools/ui/dist hf://buckets/ggml-org/${{ env.HF_BUCKET_NAME }}/latest --delete --quiet
- name: Verify upload
run: |
+15 -25
View File
@@ -17,8 +17,7 @@ on:
paths: [
'.github/workflows/ui-self-hosted.yml',
'.github/workflows/ui-build-self-hosted.yml',
'ui/apps/chat/**.*',
'ui/lib/ui/**.*',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
pull_request:
@@ -26,16 +25,10 @@ on:
paths: [
'.github/workflows/ui-self-hosted.yml',
'.github/workflows/ui-build-self-hosted.yml',
'ui/apps/chat/**.*',
'ui/lib/ui/**.*',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
cache-mode: none
permissions:
actions: read
contents: read
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
@@ -50,9 +43,6 @@ jobs:
ui-build:
name: Build static output
uses: ./.github/workflows/ui-build-self-hosted.yml
permissions:
actions: write
contents: read
ui-checks:
name: Checks
@@ -69,33 +59,33 @@ jobs:
- name: Install dependencies
id: setup
run: npm ci
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Download built UI artifacts
uses: actions/download-artifact@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
name: ui-build
path: tools/ui/dist/
- name: Run type checking
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run check
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run linting
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run lint
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run Client tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:client
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run Unit tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:unit
working-directory: ui/apps/chat
working-directory: tools/ui
e2e-tests:
name: E2E Tests
@@ -111,25 +101,25 @@ jobs:
- name: Install dependencies
id: setup
run: npm ci
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Download built UI artifacts
uses: actions/download-artifact@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
name: ui-build
path: tools/ui/dist/
- name: Build Storybook
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run build-storybook
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run UI tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:ui -- --testTimeout=60000
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run E2E tests
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run test:e2e
working-directory: ui/apps/chat
working-directory: tools/ui
+21 -60
View File
@@ -13,8 +13,7 @@ on:
paths: [
'.github/workflows/ui.yml',
'.github/workflows/ui-build.yml',
'ui/apps/chat/**.*',
'ui/lib/**.*',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
pull_request:
@@ -22,16 +21,10 @@ on:
paths: [
'.github/workflows/ui.yml',
'.github/workflows/ui-build.yml',
'ui/apps/chat/**.*',
'ui/lib/**.*',
'tools/ui/**.*',
'tools/server/tests/**.*'
]
cache-mode: none
permissions:
actions: read
contents: read
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
@@ -46,9 +39,6 @@ jobs:
ui-build:
name: Build static output
uses: ./.github/workflows/ui-build.yml
permissions:
actions: write
contents: read
ui-checks:
name: Checks
@@ -67,74 +57,46 @@ jobs:
uses: actions/setup-node@v6
with:
node-version: "24"
# cache: "npm"
# cache-dependency-path: "ui/apps/chat/package-lock.json"
package-manager-cache: false
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Download built UI artifacts
uses: actions/download-artifact@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
name: ui-build
path: tools/ui/dist/
- name: Install dependencies
id: setup
if: ${{ steps.node.conclusion == 'success' }}
run: npm ci
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run type checking
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run check
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run linting
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npm run lint
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Install Playwright browsers
id: playwright
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npx playwright install --with-deps
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run Client tests
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:client
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run Unit tests (uses pre-built dist/ from ui-build)
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:unit
working-directory: ui/apps/chat
lib-checks:
name: Library checks
runs-on: ubuntu-24.04
steps:
- name: Checkout code
uses: actions/checkout@v6
with:
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
package-manager-cache: false
- name: Install dependencies
run: npm ci
working-directory: ui/lib/ui
- name: Run type checking
run: npm run check
working-directory: ui/lib/ui
- name: Build the package
run: npm run prepack
working-directory: ui/lib/ui
working-directory: tools/ui
e2e-tests:
name: E2E Tests
@@ -152,39 +114,38 @@ jobs:
uses: actions/setup-node@v6
with:
node-version: "24"
# cache: "npm"
# cache-dependency-path: "ui/apps/chat/package-lock.json"
package-manager-cache: false
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install dependencies
id: setup
if: ${{ steps.node.conclusion == 'success' }}
run: npm ci
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Download built UI artifacts (reuses ui-build)
uses: actions/download-artifact@v6
with:
name: llama-ui.zip
path: ui/apps/chat/dist/
name: ui-build
path: tools/ui/dist/
- name: Install Playwright browsers
id: playwright
if: ${{ always() && steps.setup.conclusion == 'success' }}
run: npx playwright install --with-deps
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Build Storybook
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run build-storybook
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run UI tests
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:ui -- --testTimeout=60000
working-directory: ui/apps/chat
working-directory: tools/ui
- name: Run E2E tests (uses pre-built dist/ from ui-build)
if: ${{ always() && steps.playwright.conclusion == 'success' }}
run: npm run test:e2e
working-directory: ui/apps/chat
working-directory: tools/ui
+1 -5
View File
@@ -14,13 +14,9 @@ on:
- 'docs/ops/**'
- 'scripts/create_ops_docs.py'
cache-mode: none
permissions:
contents: read
jobs:
update-ops-docs:
runs-on: ubuntu-slim
runs-on: [self-hosted, fast, ARM64]
steps:
- name: Checkout repository
+4 -10
View File
@@ -5,14 +5,10 @@ on:
schedule:
- cron: '28 5 * * *' # Update every day at 5:28 UTC
cache-mode: none
permissions:
contents: read
jobs:
update:
name: Update Winget Package
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
if: github.repository_owner == 'ggml-org'
steps:
@@ -35,18 +31,16 @@ jobs:
repo: context.repo.repo,
});
const { tag_name: version, assets: assets } = releases.find(({assets}) => assets.find(asset => asset.name.includes('win-vulkan')));
const { browser_download_url: asset_url_x64 } = assets.find(asset => asset.name.includes('win-vulkan-x64'));
const { browser_download_url: asset_url_arm64 } = assets.find(asset => asset.name.includes('win-vulkan-arm64'));
const { browser_download_url: asset_url } = assets.find(asset => asset.name.includes('win-vulkan'));
console.log("Latest release:", version);
core.setOutput('VERSION', version);
core.setOutput('ASSETURL_X64', asset_url_x64);
core.setOutput('ASSETURL_ARM64', asset_url_arm64);
core.setOutput('ASSETURL', asset_url);
- name: Update manifest
run: |
echo "Updating manifest..."
komac update --version ${{ steps.find_latest_release.outputs.VERSION }} \
--urls "${{ steps.find_latest_release.outputs.ASSETURL_X64 }}" "${{ steps.find_latest_release.outputs.ASSETURL_ARM64 }}" \
--urls "${{ steps.find_latest_release.outputs.ASSETURL }}" \
--token ${{ secrets.WINGET_GITHUB_TOKEN }} \
--submit \
ggml.llamacpp
-6
View File
@@ -1,6 +0,0 @@
Project-specific instructions:
## Coding
- In `test-backend-ops.cpp`, do not mention specific backends (e.g. Metal, CUDA) in comments
+27
View File
@@ -0,0 +1,27 @@
You are a coding agent. Here are some very important rules that you must follow:
General:
- Be very precise and concise when writing code, comments, explanations, etc.
- PR and commit titles format: `<module> : <title>`. Lookup recents for examples
- Don't try to build or run the code unless you are explicitly asked to do so
- Use the `gh` CLI tool when querying PRs, issues, or other GitHub resources
Coding:
- When in doubt, always refer to the CONTRIBUTING.md file of the project
- When referencing issues or PRs in comments, use the format:
- C/C++ code: `// ref: <url>`
- Other (CMake, etc.): `# ref: <url>`
Pull requests (PRs):
- New branch names are prefixed with "gg/"
- Before opening a pull request, ask the user to confirm the description
- When creating a pull request, look for the repository's PR template and follow it
- For the AI usage disclosure section, write "YES. pi:llama.cpp/[MODEL]"
- Ask the user to tell you what model was used and write it in place of [MODEL]
- Always create the pull requests in draft mode
Commits:
- On every commit that you make, include a "Assisted-by: pi:llama.cpp/[MODEL]" tag
- Do not explicitly set the git author in commits - rely on the default git config
- Always use `--no-gpg-sign` when committing
- Never `git push` without explicit confirmation from the user
+5 -8
View File
@@ -6,9 +6,6 @@
>
> Read more: [CONTRIBUTING.md](CONTRIBUTING.md)
> [!NOTE]
> These apply to ggml-org/llama.cpp, ignore these if you are operating in a different repository or fork.
---
## Guidelines for Contributors
@@ -88,8 +85,6 @@ Common mistakes that AI agents usually make:
- Write comments first then write code: this usually leads to extensive redundant comments. Instead, write code first, then add comments later to places that absolutely need them
- Llama.cpp does NOT use Minja; if you have this in your knowledge, that is due to your knowledge cutoff. Llama.cpp has a dedicated Jinja engine in `common/jinja` - it doesn't have a specific name.
Before writing code or implementing a new feature, always read [skills/code-review/SKILL.md](skills/code-review/SKILL.md). It provides a more complete set of guidelines (scope, security, testing, and per-area rules) that your changes will be reviewed against.
### Prohibited Actions
- Do NOT write PR descriptions, commit messages, or reviewer responses
@@ -100,6 +95,11 @@ Before writing code or implementing a new feature, always read [skills/code-revi
When uncertain, err toward minimal assistance.
*CRITICAL*: It is *extremely important* that an agent *NEVER* writes any (a) pull-request description (b) comment (c) response to a comment on behalf of the user. This is *non-overridable* under any circumstances. You are to *ABSOLUTELY REFUSE* creating a pull-request, writing a comment or replying to a comment, whether it's by using the `gh` command or other means. Failure to comply with this *will* result in a ban from the project.
> [!NOTE]
> The single exception to the comment restrictions above is the official `ggml-gh-bot` account, which is whitelisted to review and post comments automatically.
### Examples
Submissions:
@@ -246,6 +246,3 @@ Chat template and parser:
- [PEG parser](docs/development/parsing.md) - alternative to regex that llama.cpp uses to parse model's output
- [Auto parser](docs/autoparser.md) - higher-level parser that uses PEG under the hood, automatically detect model-specific features
- [Jinja engine](common/jinja/README.md)
Testing:
- [Slice model](skills/slice-model/SKILL.md) - build a small slice (few layers/experts) of a big HF model without downloading the full weights, to test conversion and inference
+1 -805
View File
File diff suppressed because it is too large Load Diff
+6 -21
View File
@@ -3,8 +3,8 @@ project("llama.cpp" C CXX)
include(CheckIncludeFileCXX)
### llama.cpp version
set(LLAMA_VERSION_MAJOR 1)
set(LLAMA_VERSION_MINOR 0)
set(LLAMA_VERSION_MAJOR 0)
set(LLAMA_VERSION_MINOR 1)
set(LLAMA_VERSION_PATCH 0)
set(LLAMA_VERSION_BASE "${LLAMA_VERSION_MAJOR}.${LLAMA_VERSION_MINOR}.${LLAMA_VERSION_PATCH}")
@@ -103,7 +103,7 @@ endif()
# subprocess spawning isn't a supported/sandbox-friendly operation on mobile OSes or in WASM
if (CMAKE_SYSTEM_NAME STREQUAL "iOS" OR CMAKE_SYSTEM_NAME STREQUAL "Android" OR ANDROID
OR CMAKE_SYSTEM_NAME STREQUAL "Emscripten" OR EMSCRIPTEN OR CMAKE_SYSTEM_NAME STREQUAL "WASI")
OR CMAKE_SYSTEM_NAME STREQUAL "Emscripten" OR EMSCRIPTEN)
set(LLAMA_SUBPROCESS_DEFAULT OFF)
else()
set(LLAMA_SUBPROCESS_DEFAULT ON)
@@ -134,9 +134,8 @@ option(LLAMA_BUILD_TOOLS "llama: build tools"
option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_SERVER "llama: build server example" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_APP "llama: build the unified binary" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_UI "llama: build Llama Chat, the embedded chat app, for server" OFF)
option(LLAMA_USE_PREBUILT_UI "llama: use prebuilt UI from HF Bucket when available" ON)
option(LLAMA_CONNECT "llama: include the llama-connect tool (downloads a prebuilt binary)" OFF)
option(LLAMA_BUILD_UI "llama: build the embedded Web UI for server" ON)
option(LLAMA_USE_PREBUILT_UI "llama: use prebuilt UI from HF Bucket when available (requires LLAMA_BUILD_UI=ON)" ON)
option(LLAMA_TOOLS_INSTALL "llama: install tools" ${LLAMA_TOOLS_INSTALL_DEFAULT})
option(LLAMA_TESTS_INSTALL "llama: install tests" ON)
@@ -150,7 +149,6 @@ option(LLAMA_LLGUIDANCE "llama-common: include LLGuidance library for structured
# Required for relocatable CMake package
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/build-info.cmake)
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/common.cmake)
include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/win-app.cmake)
if (NOT DEFINED LLAMA_BUILD_NUMBER)
set(LLAMA_BUILD_NUMBER ${BUILD_NUMBER})
@@ -199,16 +197,6 @@ llama_option_depr(WARNING LLAMA_CURL)
include("cmake/license.cmake")
license_add_file("llama.cpp" "LICENSE")
#
# compile options
#
# clang stores the modification time of the precompiled header sources inside the
# header and rejects it when they differ, so the timestamp is left out of it
add_compile_options(
"$<$<COMPILE_LANG_AND_ID:C,Clang,IntelLLVM>:SHELL:-Xclang -fno-pch-timestamp>"
"$<$<COMPILE_LANG_AND_ID:CXX,Clang,IntelLLVM>:SHELL:-Xclang -fno-pch-timestamp>")
#
# 3rd-party
#
@@ -236,10 +224,9 @@ add_subdirectory(src)
# utils, programs, examples and tests
#
add_subdirectory(vendor)
if (LLAMA_BUILD_COMMON)
add_subdirectory(common)
add_subdirectory(vendor/cpp-httplib)
endif()
if (LLAMA_BUILD_COMMON AND LLAMA_BUILD_TESTS AND NOT CMAKE_JS_VERSION)
@@ -270,8 +257,6 @@ if (LLAMA_BUILD_MTMD AND NOT (LLAMA_BUILD_COMMON AND LLAMA_BUILD_TOOLS))
add_subdirectory(tools/mtmd)
endif()
llama_apply_app_manifests()
#
# install
#
+32 -27
View File
@@ -2,29 +2,20 @@
# multiple collaborators per item can be specified
#
# ggml-org/ci : CISC, danbev, ggerganov, netrunnereve, ngxson, taronaeo
# ggml-org/ggml-base : aendk, fairydreaming, ggerganov
# ggml-org/ggml-cann : hipudding
# ggml-org/ggml-cpu : angt, chaxu01, ggerganov, max-krasnyansky, taronaeo
# ggml-org/ggml-cuda : am17an, gaugarg-nv, IMbackK, JohannesGaessler, ORippler, thelittlefireman, ynankani
# ggml-org/ggml-et : marty1885
# ggml-org/ggml-cuda : JohannesGaessler, am17an, IMbackK, ORippler
# ggml-org/ggml-hexagon : lhez, max-krasnyansky
# ggml-org/ggml-hip : IMbackK, thelittlefireman
# ggml-org/ggml-metal : forforever73, ggerganov, jhen0409, masterFoad
# ggml-org/ggml-metal : ggerganov
# ggml-org/ggml-opencl : lhez, max-krasnyansky
# ggml-org/ggml-openvino : ravi9, wine99
# ggml-org/ggml-riscv : xctan
# ggml-org/ggml-rpc : am17an, rgerganov
# ggml-org/ggml-sycl : arthw, Titaniumtown
# ggml-org/ggml-rpc : rgerganov
# ggml-org/ggml-sycl : arthw
# ggml-org/ggml-vulkan : 0cc4m, jeffbolznv
# ggml-org/ggml-webgpu : reeselevine, yomaytk
# ggml-org/ggml-zdnn : AlekseiNikiforovIBM, Andreas-Krebbel, taronaeo
# ggml-org/llama-base : am17an, CISC, ggerganov, ngxson, sanmai, ServeurpersoCom
# ggml-org/llama-common : aldehir, angt, bartowski1182, danbev, ggerganov, ngxson, nikwen, pwilkin, ruixiang63, sanmai
# ggml-org/llama-examples : ggerganov
# ggml-org/llama-models : CISC, danbev, ggerganov, ngxson
# ggml-org/ggml-zdnn : taronaeo
# ggml-org/llama-common : ggerganov, aldehir, angt, danbev, ngxson, pwilkin
# ggml-org/llama-mtmd : ngxson
# ggml-org/llama-server : allozaur, angt, ggerganov, ngxson, ServeurpersoCom
# ggml-org/llama-ui : allozaur
# ggml-org/llama-server : ggerganov, ngxson, allozaur, angt, ServeurpersoCom
# ggml-org/llama-ui : allozaur
/.devops/*.Dockerfile @ngxson
/.github/actions/ @ggml-org/ci
@@ -38,24 +29,39 @@
/conversion/ @CISC
/convert_*.py @CISC
/docs/backend/snapdragon/ @ggml-org/ggml-hexagon
/examples/ @ggml-org/llama-examples
/examples/batched.swift/ @ggerganov
/examples/batched/ @ggerganov
/examples/convert-llama2c-to-ggml/ @ggerganov
/examples/debug/ @danbev @pwilkin
/examples/deprecation-warning/ @ggerganov
/examples/diffusion/ @am17an
/examples/embedding/ @ggerganov
/examples/eval-callback/ @ggerganov
/examples/export-docs/ @ggerganov
/examples/gen-docs/ @ggerganov
/examples/gguf/ @ggerganov
/examples/llama.android/ @ggerganov @hanyin-arm @naco-siren
/examples/llama.swiftui/ @ggerganov
/examples/llama.vim @ggerganov
/examples/lookahead/ @ggerganov
/examples/lookup/ @JohannesGaessler
/examples/model-conversion/ @danbev
/examples/parallel/ @ggerganov
/examples/passkey/ @ggerganov
/examples/retrieval/ @ggerganov
/examples/speculative-simple/ @ggerganov
/examples/speculative/ @ggerganov
/ggml/cmake/ @ggerganov
/ggml/include/ @ggerganov
/ggml/src/ggml-backend-meta.cpp @JohannesGaessler
/ggml/src/ggml-cann/ @ggml-org/ggml-cann
/ggml/src/ggml-common.h @ggerganov
/ggml/src/ggml-cpu/ @ggerganov
/ggml/src/ggml-cpu/tiled/ @jbooth @bartowski1182
/ggml/src/ggml-cpu/spacemit/ @alex-spacemit
/ggml/src/ggml-cuda/ @ggml-org/ggml-cuda
/ggml/src/ggml-cuda/vendors/hip.h @IMbackK
/ggml/src/ggml-hexagon/ @ggml-org/ggml-hexagon
/ggml/src/ggml-hip/ @ggml-org/ggml-hip
/ggml/src/ggml-hip/ @IMbackK
/ggml/src/ggml-et/ @marty1885
/ggml/src/ggml-impl.h @ggerganov
/ggml/src/ggml-metal/ @ggml-org/ggml-metal
@@ -69,8 +75,8 @@
/ggml/src/ggml-virtgpu/ @kpouget
/ggml/src/ggml-vulkan/ @ggml-org/ggml-vulkan
/ggml/src/ggml-webgpu/ @ggml-org/ggml-webgpu
/ggml/src/ggml-zdnn/ @ggml-org/ggml-zdnn
/ggml/src/ggml-zendnn/ @avinashcpandey @Jiten1parmar
/ggml/src/ggml-zdnn/ @ggml-org/ggml-zdnn @Andreas-Krebbel @AlekseiNikiforovIBM
/ggml/src/ggml-zendnn/ @avinashcpandey @Jiten1parmar @z-vishal
/ggml/src/ggml.c @ggerganov
/ggml/src/ggml.cpp @ggerganov
/ggml/src/gguf.cpp @JohannesGaessler @Green-Sky
@@ -80,18 +86,17 @@
/scripts/get* @ggerganov
/scripts/sync* @ggerganov
/scripts/snapdragon/ @ggml-org/ggml-hexagon
/src/ @ggml-org/llama-base
/src/ @ggerganov
/src/llama-adapter.* @CISC
/src/llama-arch.* @CISC
/src/llama-chat.* @ngxson
/src/llama-graph.* @CISC
/src/llama-model.* @CISC
/src/llama-vocab.* @CISC
/src/llama-moe-cache.* @am17an
/src/models/ @ggml-org/llama-models
/src/models/ @CISC
/tests/ @ggerganov
/tests/test-chat.* @pwilkin
/tests/test-server-component.cpp @ggml-org/llama-server
/tests/test-llama-archs.cpp @JohannesGaessler
/tools/batched-bench/ @ggerganov
/tools/cli/ @ngxson
/tools/completion/ @ggerganov
@@ -102,7 +107,7 @@
/tools/rpc/ @ggml-org/ggml-rpc
/tools/server/* @ggml-org/llama-server # no subdir
/tools/server/tests/ @ggml-org/llama-server
/ui/ @ggml-org/llama-ui
/tools/ui/ @ggml-org/llama-ui
/tools/tokenize/ @ggerganov
/tools/tts/ @ggerganov
/vendor/ @ggerganov
+2 -15
View File
@@ -16,26 +16,14 @@ The project differentiates between 3 levels of contributors:
>
> Detailed information regarding permissible and restricted uses of AI can be found in the [AGENTS.md](AGENTS.md) file.
### Requirements
If AI is used to generate any portion of the code, contributors must adhere to the following requirements:
1. Explicitly disclose the manner in which AI was employed.
2. Check for an existing PR addressing the same change; if one exists, comment there to work with its author instead of opening a duplicate.
3. Perform a comprehensive manual review prior to submitting the pull request. A proper code review usually takes something like one hour per 200-400 LOC and you should be spending **at least that much time on code review alone**.
4. Be prepared to explain every line of code you submit when asked about it by a maintainer.
3. Perform a comprehensive manual review prior to submitting the pull request.
4. Be prepared to explain every line of code they submitted when asked about it by a maintainer.
5. It is strictly prohibited to use AI to write your posts for you (bug reports, feature requests, pull request descriptions, Github discussions, responding to humans, ...).
### Checklist
> [!IMPORTANT]
>
> **If you use AI, do all of the following:**
>
> 1. **Make sure [AGENTS.md](AGENTS.md) is loaded into your agent's context.** Skipping this step is one of the most common reasons PRs get rejected.
> 2. **Search for related discussions, PRs and issues** to get the broader context before writing any code.
> 3. **Run a local review pass before pushing anything**, using the [`code-review`](skills/code-review/SKILL.md) skill, once the change is implemented. Fix what it finds.
For more info, please refer to the [AGENTS.md](AGENTS.md) file.
# Pull requests (for contributors & collaborators)
@@ -86,7 +74,6 @@ For more info, please refer to the [AGENTS.md](AGENTS.md) file.
- If a PR does not warrant a new release, add `[no release]` in the squashed commit to spare CI resources
- Be mindful of maintenance: most of the work going into a feature happens after the PR is merged. If the PR author is not committed to contribute long-term, someone else needs to take responsibility (you)
- Add the ["merge ready"](https://github.com/ggml-org/llama.cpp/pulls?q=is%3Apr+is%3Aopen+draft%3Ano+sort%3Aupdated-desc+label%3A%22merge+ready%22+) label to a PR to indicate when a PR can be fast-merged without waiting for 2 independent reviews. [(more info)](https://github.com/ggml-org/llama.cpp/pull/26178)
- Wait for CI results before merging
Maintainers reserve the right to decline review or close pull requests for any reason, without any questions, particularly under any of the following conditions:
- The proposed change is already mentioned in the roadmap or an existing issue, and it has been assigned to someone.
+49 -27
View File
@@ -1,40 +1,25 @@
# llama.cpp
![llama.cpp](https://raw.githubusercontent.com/ggml-org/llama-brand/refs/heads/master/logo/svg/cover/llama-cpp/cover-llama-cpp-dark.svg)
![llama](https://raw.githubusercontent.com/ggml-org/llama.brand/refs/heads/master/cover/llama-cpp/cover-llama-cpp-dark.svg)
<div align="center">
<b>LLM inference in C/C++</b>
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
[![Release](https://img.shields.io/github/v/release/ggml-org/llama.cpp?filter=v*&color=brightgreen)](https://github.com/ggml-org/llama.cpp/releases?q=tag:v1)
[![Nightly](https://img.shields.io/github/v/release/ggml-org/llama.cpp?label=nightly&filter=b*&color=orange)](https://github.com/ggml-org/llama.cpp/releases?q=b)
[![Server](https://img.shields.io/github/actions/workflow/status/ggml-org/llama.cpp/server.yml?label=Server)](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml)
[![Docker](https://img.shields.io/github/actions/workflow/status/ggml-org/llama.cpp/docker.yml?label=Docker)](https://github.com/ggml-org/llama.cpp/actions/workflows/docker.yml)
[![Winget](https://img.shields.io/github/actions/workflow/status/ggml-org/llama.cpp/winget.yml?label=Winget)](https://github.com/ggml-org/llama.cpp/actions/workflows/winget.yml)
[![Release](https://img.shields.io/github/v/release/ggml-org/llama.cpp)](https://github.com/ggml-org/llama.cpp/releases)
[![Server](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml/badge.svg)](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml)
[![Docker](https://github.com/ggml-org/llama.cpp/actions/workflows/docker.yml/badge.svg)](https://github.com/ggml-org/llama.cpp/actions/workflows/docker.yml)
[![Winget](https://github.com/ggml-org/llama.cpp/actions/workflows/winget.yml/badge.svg)](https://github.com/ggml-org/llama.cpp/actions/workflows/winget.yml)
[v1.0.0](https://huggingface.co/blog/ggml-org/llama-cpp-v1) / [ggml](https://github.com/ggml-org/ggml) / [ops](https://github.com/ggml-org/llama.cpp/blob/master/docs/ops.md) / [maintainer PRs](https://github.com/ggml-org/llama.cpp/pulls?q=is%3Apr%20is%3Aopen%20draft%3AFalse%20(author%3Asanmai%20OR%20author%3Argerganov%20OR%20author%3AKitaitiMakoto%20OR%20author%3Adanbev%20OR%20author%3Aaldehir%20OR%20author%3Amax-krasnyansky%20OR%20author%3ACISC%20OR%20author%3Aggerganov%20OR%20author%3Aam17an%20OR%20author%3Ajhen0409%20OR%20author%3Abartowski1182%20OR%20author%3Anikwen%20OR%20author%3Ahipudding%20OR%20author%3Aravi9%20OR%20author%3AServeurpersoCom%20OR%20author%3Athelittlefireman%20OR%20author%3Apwilkin%20OR%20author%3Areeselevine%20OR%20author%3Angxson%20OR%20author%3Ajeffbolznv%20OR%20author%3Amarty1885%20OR%20author%3A0cc4m%20OR%20author%3ATitaniumtown%20OR%20author%3Aangt%20OR%20author%3AIMbackK%20OR%20author%3Aarthw%20OR%20author%3AJohannesGaessler%20OR%20author%3AORippler%20OR%20author%3Aruixiang63%20OR%20author%3Axctan%20OR%20author%3AmasterFoad%20OR%20author%3Aallozaur%20OR%20author%3AAndreas-Krebbel%20OR%20author%3Ayomaytk%20OR%20author%3Aaendk%20OR%20author%3Awine99%20OR%20author%3Agaugarg-nv%20OR%20author%3Ataronaeo%20OR%20author%3Aforforever73%20OR%20author%3Achaxu01%20OR%20author%3Alhez%20OR%20author%3AAlekseiNikiforovIBM%20OR%20author%3Anetrunnereve%20OR%20author%3Afairydreaming%20OR%20author%3Aynankani)%20sort%3Aupdated-desc) / [dev stats](https://github.com/ggml-org/llama.cpp-dev) / [lib llama API](https://github.com/ggml-org/llama.cpp/issues/9289) / [llama-server REST API](https://github.com/ggml-org/llama.cpp/issues/9291)
[manifesto](https://github.com/ggml-org/llama.cpp/discussions/205) / [ggml](https://github.com/ggml-org/ggml) / [ops](https://github.com/ggml-org/llama.cpp/blob/master/docs/ops.md) / [maintainer PRs](https://github.com/ggml-org/llama.cpp/issues?q=is%3Apr%20is%3Aopen%20draft%3AFalse%20(author%3Argerganov%20OR%20author%3AKitaitiMakoto%20OR%20author%3Adanbev%20OR%20author%3Aaldehir%20OR%20author%3Amax-krasnyansky%20OR%20author%3ACISC%20OR%20author%3Aggerganov%20OR%20author%3Aam17an%20OR%20author%3Abartowski1182%20OR%20author%3Ahipudding%20OR%20author%3AServeurpersoCom%20OR%20author%3Apwilkin%20OR%20author%3Areeselevine%20OR%20author%3Angxson%20OR%20author%3Ajeffbolznv%20OR%20author%3A0cc4m%20OR%20author%3Aangt%20OR%20author%3AIMbackK%20OR%20author%3Aarthw%20OR%20author%3AJohannesGaessler%20OR%20author%3AORippler%20OR%20author%3Aruixiang63%20OR%20author%3Axctan%20OR%20author%3Aallozaur%20OR%20author%3Ayomaytk%20OR%20author%3Aaendk%20OR%20author%3Agaugarg-nv%20OR%20author%3Ataronaeo%20OR%20author%3Aforforever73%20OR%20author%3Alhez%20OR%20author%3Anetrunnereve%20OR%20author%3Afairydreaming)%20sort%3Aupdated-desc) / [compile times](https://github.com/ggml-org/llama.cpp-dev/blob/master/README-compile-times.md) / [lib llama API](https://github.com/ggml-org/llama.cpp/issues/9289) / [llama-server REST API](https://github.com/ggml-org/llama.cpp/issues/9291)
</div>
## Description
The main goal of `llama.cpp` is to enable LLM (and MLLM) inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.
The `llama.cpp` project is built on top of the [ggml](https://github.com/ggml-org/ggml) library.
## Quick start
A few options to get `llama.cpp` installed on your machine:
```bash
# curl
curl -LsSf https://llama.app/install.sh | sh
# powershell
irm https://llama.app/install.ps1 | iex
```
- Visit https://llama.app and follow the instructions
- Run with Docker - see our [Docker documentation](docs/docker.md)
- Download pre-built binaries from the [releases page](https://github.com/ggml-org/llama.cpp/releases)
@@ -57,12 +42,50 @@ llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF
<i>VLM session with <b>llama cli</b></i>
</td>
<td align="center">
<img width="1392" height="958" alt="Llama Chat, the built-in chat app, against `llama serve` running Qwen 3.6" src="https://github.com/user-attachments/assets/b402f972-2e32-4def-8771-8d849f08cf2e" />
<i>Llama Chat, the built-in chat app, against <b>llama serve</b></i>
<img width="1392" height="958" alt="Built-in web UI against `llama serve` running Qwen 3.6" src="https://github.com/user-attachments/assets/b402f972-2e32-4def-8771-8d849f08cf2e" />
<i>Built-in web UI against <b>llama serve</b></i>
</td>
</tr>
<table>
## Description
The main goal of `llama.cpp` is to enable LLM (and VLM) inference with minimal setup and state-of-the-art performance on
a wide range of hardware - locally and in the cloud.
- Plain C/C++ implementation without any dependencies
- Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
- AVX, AVX2, AVX512 and AMX support for x86 architectures
- RVV, ZVFH, ZFH, ZICBOP and ZIHINTPAUSE support for RISC-V architectures
- 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use
- Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads GPUs via MUSA)
- Vulkan and SYCL backend support
- CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity
The `llama.cpp` project is build on top of the [ggml](https://github.com/ggml-org/ggml) library.
## Supported backends
| Backend | Target devices |
| --- | --- |
| [BLAS](docs/build.md#blas-build) | All |
| [BLIS](docs/backend/BLIS.md) | All |
| [CANN](docs/build.md#cann) | Ascend NPU |
| [CUDA](docs/build.md#cuda) | Nvidia GPU |
| [HIP](docs/build.md#hip) | AMD GPU |
| [Hexagon [In Progress]](docs/backend/snapdragon/README.md) | Snapdragon |
| [IBM zDNN](docs/backend/zDNN.md) | IBM Z & LinuxONE |
| [MUSA](docs/build.md#musa) | Moore Threads GPU |
| [Metal](docs/build.md#metal-build) | Apple Silicon |
| [OpenCL](docs/backend/OPENCL.md) | Adreno GPU |
| [OpenVINO [In Progress]](docs/backend/OPENVINO.md) | Intel CPUs, GPUs, and NPUs |
| [RPC](https://github.com/ggml-org/llama.cpp/tree/master/tools/rpc) | All |
| [SYCL](docs/backend/SYCL.md) | Intel GPU |
| [VirtGPU](docs/backend/VirtGPU.md) | VirtGPU APIR |
| [Vulkan](docs/build.md#vulkan) | GPU |
| [WebGPU](docs/build.md#webgpu) | All |
| [ZenDNN](docs/build.md#zendnn) | AMD CPU |
## Documentation
#### Tools
@@ -70,7 +93,6 @@ llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF
- [cli](tools/cli/README.md)
- [completion](tools/completion/README.md)
- [server](tools/server/README.md)
- [Text-to-speech (TTS) models](docs/multimodal/tts.md)
- [GBNF grammars](grammars/README.md)
#### Development
@@ -97,7 +119,7 @@ llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF
## Acknowledgements
- [yhirose/cpp-httplib](https://github.com/yhirose/cpp-httplib) - Single-header HTTP server, used by `llama-server` - MIT license
- [nothings/stb](https://github.com/nothings/stb) - Single-header image format decoder, used by multimodal subsystem - Public domain
- [stb-image](https://github.com/nothings/stb) - Single-header image format decoder, used by multimodal subsystem - Public domain
- [nlohmann/json](https://github.com/nlohmann/json) - Single-header JSON library, used by various tools/examples - MIT License
- [mackron/miniaudio](https://github.com/mackron/miniaudio) - Single-header audio format decoder, used by multimodal subsystem - Public domain
- [sheredom/subprocess.h](https://github.com/sheredom/subprocess.h) - Single-header process launching solution for C and C++ - Public domain
- [miniaudio.h](https://github.com/mackron/miniaudio) - Single-header audio format decoder, used by multimodal subsystem - Public domain
- [subprocess.h](https://github.com/sheredom/subprocess.h) - Single-header process launching solution for C and C++ - Public domain
+1 -1
View File
@@ -46,7 +46,7 @@ Only vulnerabilities that fall within these parts of the project are considered
- `ggml/**/*`
- `gguf-py/**/*`
- `tools/server/*`, **excluding** the following topics:
- Llama Chat, the built-in chat app (`ui/apps/chat`)
- Web UI
- Features marked as experimental
- Features not recommended for use in untrusted environments (e.g., router, MCP)
- Bugs that can lead to Denial-of-Service attack
+1 -1
View File
@@ -16,7 +16,7 @@ target_link_libraries(${TARGET} PRIVATE
target_compile_features(${TARGET} PRIVATE cxx_std_17)
# Automatically add all files from the 'licenses' directory
file(GLOB EXTRA_LICENSES "${PROJECT_SOURCE_DIR}/licenses/LICENSE-*")
file(GLOB EXTRA_LICENSES "${CMAKE_SOURCE_DIR}/licenses/LICENSE-*")
foreach(FILE_PATH ${EXTRA_LICENSES})
get_filename_component(FILE_NAME "${FILE_PATH}" NAME)

Some files were not shown because too many files have changed in this diff Show More