upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-01 02:17:42 -05:00
Code Issues Packages Projects Releases Wiki Activity
11,323 Commits 825 Branches 7,693 Tags

Default Branch

master

f11d642a27 · HIP: avoid treating CDNA as dgx spark for gqa_ratio 20 in fattn_mma dqk 576 (#29572) · Updated 2026-10-01 00:51:38 -05:00
 ZIP  TAR.GZ

Branches

xsn/ci_legacy_gg

8654805027 · docker : publish to both ggerganov and ggml-org · Updated 2025-02-15 08:18:04 -06:00    upstream-archive

6623
1
 ZIP  TAR.GZ
revert-11820-vers_fix

f30aca84b2 · Revert "HIP: Switch to std::vector in rocblas version check (#11820)" · Updated 2025-02-12 12:22:04 -06:00    upstream-archive

6627
1
 ZIP  TAR.GZ
gg/server-logs

d86e23101e · server : minor log updates · Updated 2025-02-08 08:23:37 -06:00    upstream-archive

6653
1
 ZIP  TAR.GZ
gg/llama-add-log

3b6a0a817a · llama : add log about loading model tensors · Updated 2025-02-06 01:24:07 -06:00    upstream-archive

6674
1
 ZIP  TAR.GZ
podman

947158ee52 · Specify podman works in Container documentation · Updated 2025-02-05 07:47:21 -06:00    upstream-archive

6679
1
 ZIP  TAR.GZ
sl/pr-releases

de9d2c6f09 · test [pack] · Updated 2025-01-24 16:24:31 -06:00    upstream-archive

6776
3
 ZIP  TAR.GZ
gg/build-pack-lib-include

969b264657 · Revert "TMP : push artifacts" · Updated 2025-01-24 09:58:09 -06:00    upstream-archive

6782
15
 ZIP  TAR.GZ
gg/build-linux-static

ff4cb6ef4c · release : pack /lib and /include in the packages · Updated 2025-01-24 05:28:37 -06:00    upstream-archive

6782
1
 ZIP  TAR.GZ
xsn/tmp_jinja_safer

c9e7cbb08b · safer jinja llama_chat_templates struct · Updated 2025-01-20 09:58:29 -06:00    upstream-archive

6821
34
 ZIP  TAR.GZ
cedo/add-outetts-v0.3

90a0349349 · recommended way to check if the version is 0.3, as requested by ngxson · Updated 2025-01-19 07:43:59 -06:00    upstream-archive

6819
2
 ZIP  TAR.GZ
jg/llama-sanitize

ba421dd04e · gguf-test: tensor data comparison · Updated 2025-01-18 02:49:47 -06:00    upstream-archive

6821
7
 ZIP  TAR.GZ
gg/ci-python

492eaad571 · ci : change python3 -> python · Updated 2025-01-15 08:18:56 -06:00    upstream-archive

6835
1
 ZIP  TAR.GZ
gg/vocab-fix-no-vocab

0cf9a06799 · vocab : minor [no ci] · Updated 2025-01-14 02:36:28 -06:00    upstream-archive

6844
2
 ZIP  TAR.GZ
gg/llama-shadow-on

a97b3621cf · ggml : ggml_backend_graph_copy -> ggml_backend_graph_copy_state · Updated 2025-01-12 09:57:51 -06:00    upstream-archive

6859
15
 ZIP  TAR.GZ
0cc4m/vulkan-renderdoc

9af90481d0 · Vulkan: Add renderdoc tracing support · Updated 2025-01-12 07:47:36 -06:00    upstream-archive

6861
1
 ZIP  TAR.GZ
compilade/cuda-tq2_0

fbddb26250 · ggml-cuda : use i and j instead of i0 and i in vec_dot_tq2_0_q8_1 · Updated 2025-01-11 20:06:49 -06:00    upstream-archive

6868
7
 ZIP  TAR.GZ
shards-lang/gio/visionos-ci

9605c5fb28 · cmake : remove explicit _XOPEN_SOURCE · Updated 2025-01-06 05:02:48 -06:00    upstream-archive

6913
2
 ZIP  TAR.GZ
0cc4m/vulkan-instance-cleanup

aa014d7e89 · Use mutex instead of atomics for vk_instance counters · Updated 2024-12-29 23:14:58 -06:00    upstream-archive

6926
2
 ZIP  TAR.GZ
0cc4m/vulkan-coopmat-amd-windows

fe9235d795 · Force max subgroup size for coopmat shaders · Updated 2024-12-18 01:26:27 -06:00    upstream-archive

6972
1
 ZIP  TAR.GZ
gg/cpu-fix-cpy-iq

4fbb801a9d · ggml : update ggml_backend_cpu_device_supports_op · Updated 2024-12-17 10:09:02 -06:00    upstream-archive

6982
3
 ZIP  TAR.GZ