upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-28 17:07:31 -05:00
Code Issues Packages Projects Releases Wiki Activity
Files
rpc_tensor
llama.cpp/tests/CMakeLists.txt
T
jboothandGeorgi Gerganov d834d44e64 ggml-cpu: tiled mul_mat for k-quants (#27851) 
* Added tiled mul_mat.

For each mul_mat_one_chunk, quants are unpacked into (max) 256x256 tiles of int8,
one routine per quent.  Then microkernel computes 16x16 tiles before writing out
256x256 float reults to main memory.

Tests/benches in tests/test-tiled-mulmat.cpp.  3-6x speed improvement
for large matmul, break even at 4096x64 * 64x4096, 80% performance (net
loss) for GEMV.  Error rates trivial (order of 1-e04 max, 1-e05 rmse).

* Fixes for ARM/windows builds

* more windows fixes, ggml-cpu.h isn't visible in MSVC for some reason

* unified iqp + tiled on the Q5_K, IQ4_XS set for benchmarking, updated benchmark

* Fixed accidental removal of llama_build_and_test(test-backend-ops.cpp)

* First integration of iqp code

Co-authored-by Bartowski <3266127+bartowski1182@users.noreply.github.com>

* Cleaning up declaration of iq unpacking helpers to align with the bit unpackers

* Removed iqp path

* Fix cross-platform warnings

* Disabling benchmarks unless explicitly enabled

* Fix backend_init for DLL-based builds, add self and bartowski to CODEOWNERS for tiled

* Put benchmarks behind a flag

* kernel fix for AVX2, iq quants

* Fix for asan, leaking memory in test-tiled-mulmat and avoid stack use after return

* guarding env flags with std::call_once

* Simplified repacking for VNNI to a single call per macrotile

* No threadlocals anymore, aligned wdata access

* Doing aligned reads since we ensure alignment with padding in wdata

* Eliminated per-thread gather of Q8_K rows in mul_mat_id, we now gather/repack in a single pass.  Repack method now takes pointer array to support both dense/normal and mmid paths.  Interface with ggml-cpu.c simplified as a result

* Unified/simplified dispatch and support checks.  Put details on wdata needed inside the kernel.h body, simplified interactions with ggml-cpu.c.

* Cleanup includes and whitespace, update src1_repack to return false if we don't need a special repack, so the common case is handled by driver

* Better detection of win32 and additional whitespace fixes

* Gating fuzz tests behind a parameter and some extra prints to try and fix slow CI hosts

* Optimized AVX2 kernel

* Changed interleave format and added ability to interleave in-place after dequant

* Repacks now happen in-place, 16x64 microtiles are independent of each other

* Only repack rows in groups of 16 as they're needed.  Save work in low n_rows cases and optimize L1 usage in other cases

* Use long panels for memory-bound regime (M <= 16), reintroduce IQP path for benchmarks

* Fix unused warnings and cleanup.  Improved IQ dequantization speed.

* Removed separate process benchmarks

* Revert "Removed separate process benchmarks"

This reverts commit 0688cf43d5.

* AVX2 optimizations and guards for tests on windows

* Removed temp perf harness

* Remove perf-mulmat from build

* Removed IQP path, simplified tests to not use sub processes

* Cleaning up alignment of wdata

* Whitespace fixes and aligning L2 workspace to clean 512kb boundaries

* Update ggml/src/ggml-cpu/tiled/tiled-kernel.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Cleanup merge-duplicated declaration of test-backend-ops target

* Undo accidental line deletion in ggml.c

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-09-26 08:38:57 +03:00

383 lines
16 KiB
CMake
Raw Permalink Blame History

llama_add_compile_flags()
function(llama_build source)
set(TEST_SOURCES ${source} ${ARGN})
if (DEFINED LLAMA_TEST_NAME)
set(TEST_TARGET ${LLAMA_TEST_NAME})
else()
get_filename_component(TEST_TARGET ${source} NAME_WE)
endif()
add_executable(${TEST_TARGET} ${TEST_SOURCES})
target_link_libraries(${TEST_TARGET} PRIVATE llama llama-common) # TODO: [TAG_TESTS_LLAMA_LINK]
if (LLAMA_TESTS_INSTALL)
install(TARGETS ${TEST_TARGET} RUNTIME)
endif()
endfunction()
function(llama_test target)
include(CMakeParseArguments)
set(options)
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
set(multiValueArgs ARGS)
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
if (NOT DEFINED LLAMA_TEST_LABEL)
set(LLAMA_TEST_LABEL "main")
endif()
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
set(LLAMA_TEST_WORKING_DIRECTORY .)
endif()
if (DEFINED LLAMA_TEST_NAME)
set(TEST_NAME ${LLAMA_TEST_NAME})
else()
set(TEST_NAME ${target})
endif()
set(TEST_TARGET ${target})
add_test(
NAME ${TEST_NAME}
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
COMMAND $<TARGET_FILE:${TEST_TARGET}>
${LLAMA_TEST_ARGS})
set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
endfunction()
function(llama_test_cmd target)
include(CMakeParseArguments)
set(options)
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
set(multiValueArgs ARGS)
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
if (NOT DEFINED LLAMA_TEST_LABEL)
set(LLAMA_TEST_LABEL "main")
endif()
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
set(LLAMA_TEST_WORKING_DIRECTORY .)
endif()
if (DEFINED LLAMA_TEST_NAME)
set(TEST_NAME ${LLAMA_TEST_NAME})
else()
set(TEST_NAME ${target})
endif()
add_test(
NAME ${TEST_NAME}
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
COMMAND ${target}
${LLAMA_TEST_ARGS})
set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
endfunction()
# Builds and runs a test source file.
# Optional args:
# - NAME: name of the executable & test target (defaults to the source file name without extension)
# - LABEL: label for the test (defaults to main)
# - ARGS: arguments to pass to the test executable
# - WORKING_DIRECTORY
function(llama_build_and_test source)
include(CMakeParseArguments)
set(options)
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
set(multiValueArgs ARGS)
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
set(TEST_SOURCES ${source} ${LLAMA_TEST_UNPARSED_ARGUMENTS})
if (NOT DEFINED LLAMA_TEST_LABEL)
set(LLAMA_TEST_LABEL "main")
endif()
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
set(LLAMA_TEST_WORKING_DIRECTORY .)
endif()
if (DEFINED LLAMA_TEST_NAME)
set(TEST_TARGET ${LLAMA_TEST_NAME})
else()
get_filename_component(TEST_TARGET ${source} NAME_WE)
endif()
add_executable(${TEST_TARGET} ${TEST_SOURCES})
if (LLAMA_TESTS_INSTALL)
install(TARGETS ${TEST_TARGET} RUNTIME)
endif()
target_link_libraries(${TEST_TARGET} PRIVATE llama-common)
add_test(
NAME ${TEST_TARGET}
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
COMMAND $<TARGET_FILE:${TEST_TARGET}>
${LLAMA_TEST_ARGS})
set_property(TEST ${TEST_TARGET} PROPERTY LABELS ${LLAMA_TEST_LABEL})
endfunction()
# build test-tokenizer-0 target once and add many tests
llama_build(test-tokenizer-0.cpp)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-bert-bge.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-command-r.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-coder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-coder.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-llm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-llm.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-falcon ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gemma-4 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gemma-4.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-phi-3.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen2.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen35 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen35.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-starcoder.gguf)
if (NOT WIN32)
llama_test_cmd(
${CMAKE_CURRENT_SOURCE_DIR}/test-tokenizers-repo.sh
NAME test-tokenizers-ggml-vocabs
WORKING_DIRECTORY ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}
ARGS https://huggingface.co/ggml-org/vocabs ${PROJECT_SOURCE_DIR}/models/ggml-vocabs
)
endif()
if (LLAMA_LLGUIDANCE)
llama_build_and_test(test-grammar-llguidance.cpp ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf)
endif ()
llama_build(test-recurrent-state-rollback.cpp)
llama_build(test-save-load-state.cpp)
if (NOT WIN32 OR NOT BUILD_SHARED_LIBS)
# these tests are disabled on Windows because they use internal functions not exported with LLAMA_API (when building with shared libraries)
llama_build_and_test(test-unicode.cpp)
llama_build_and_test(test-sampling.cpp)
llama_build_and_test(test-reasoning-budget.cpp)
llama_build_and_test(test-grammar-parser.cpp)
llama_build_and_test(test-grammar-integration.cpp)
llama_build_and_test(test-llama-grammar.cpp)
llama_build_and_test(test-batch-alloc.cpp)
llama_build_and_test(test-chat.cpp WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
target_include_directories(test-chat PRIVATE ${PROJECT_SOURCE_DIR}/tools/server)
target_link_libraries(test-chat PRIVATE server-context)
llama_build_and_test(test-json-schema-to-grammar.cpp)
if (NOT GGML_BACKEND_DL)
llama_build(test-quantize-stats.cpp)
endif()
llama_build(test-gbnf-validator.cpp)
# build test-tokenizer-1-bpe target once and add many tests
llama_build(test-tokenizer-1-bpe.cpp)
# TODO: disabled due to slowness
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-aquila ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-aquila.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-falcon ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-neox ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-neox.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-llama-bpe ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf --ignore-merges)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-mpt ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-refact ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-starcoder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-starcoder.gguf)
# build test-tokenizer-1-spm target once and add many tests
llama_build(test-tokenizer-1-spm.cpp)
llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-llama-spm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf)
#llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-baichuan ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-baichuan.gguf)
# llama_build_and_test(test-double-float.cpp) # SLOW
llama_build(test-llama-archs.cpp)
set(MODEL_DIR "${CMAKE_CURRENT_BINARY_DIR}/test-models/")
file(MAKE_DIRECTORY "${MODEL_DIR}")
llama_test(
test-llama-archs
NAME test-generate-models
LABEL main
ARGS -o "${MODEL_DIR}"
)
set_tests_properties(test-generate-models PROPERTIES
FIXTURES_SETUP generate-models
)
llama_test(
test-recurrent-state-rollback
LABEL main
ARGS -m "${MODEL_DIR}/qwen35-dense.gguf"
)
set_tests_properties(test-recurrent-state-rollback PROPERTIES
FIXTURES_REQUIRED generate-models
)
llama_test(
test-recurrent-state-rollback
NAME test-recurrent-state-rollback-nemotron-h
LABEL main
ARGS -m "${MODEL_DIR}/nemotron_h-dense.gguf"
)
set_tests_properties(test-recurrent-state-rollback-nemotron-h PROPERTIES
FIXTURES_REQUIRED generate-models
)
llama_test(
test-recurrent-state-rollback
NAME test-recurrent-state-rollback-dsv4
LABEL main
ARGS -m "${MODEL_DIR}/deepseek4-moe.gguf"
)
set_tests_properties(test-recurrent-state-rollback-dsv4 PROPERTIES
FIXTURES_REQUIRED generate-models
)
llama_test(
test-recurrent-state-rollback
NAME test-recurrent-state-rollback-kimi-k3
LABEL main
ARGS -m "${MODEL_DIR}/kimi-k3-moe.gguf"
)
set_tests_properties(test-recurrent-state-rollback-kimi-k3 PROPERTIES
FIXTURES_REQUIRED generate-models
)
# Test state save/load functionality across all architectures, using the generated dummy models
llama_test(
test-save-load-state
LABEL main
ARGS --models "${MODEL_DIR}"
)
set_tests_properties(test-save-load-state PROPERTIES FIXTURES_REQUIRED generate-models)
llama_build(test-fusion.cpp)
endif()
llama_build_and_test(test-chat-peg-parser.cpp peg-parser/simple-tokenize.cpp)
llama_build_and_test(test-jinja.cpp)
llama_test(test-jinja NAME test-jinja-py ARGS -py LABEL python)
llama_build_and_test(test-json-schema.cpp)
llama_build_and_test(test-chat-auto-parser.cpp WORKING_DIRECTORY ${PROJECT_SOURCE_DIR})
llama_build_and_test(test-chat-template.cpp)
# debug tool for chat template differential analysis (not registered as a test, run it manually)
llama_build(test-chat-analysis.cpp)
llama_build_and_test(test-log.cpp)
llama_build_and_test(
test-peg-parser.cpp
peg-parser/simple-tokenize.cpp
peg-parser/test-basic.cpp
peg-parser/test-gbnf-generation.cpp
peg-parser/test-json-parser.cpp
peg-parser/test-json-serialization.cpp
peg-parser/test-python-dict-parser.cpp
peg-parser/test-unicode.cpp
peg-parser/tests.h
)
if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "s390x")
set(MODEL_NAME "tinyllamas/stories15M-q4_0.gguf")
set(MODEL_HASH "SHA256=66967fbece6dbe97886593fdbb73589584927e29119ec31f08090732d1861739")
else()
set(MODEL_NAME "tinyllamas/stories15M-be.Q4_0.gguf")
set(MODEL_HASH "SHA256=9aec857937849d976f30397e97eb1cabb53eb9dcb1ce4611ba8247fb5f44c65d")
endif()
set(MODEL_DEST "${CMAKE_BINARY_DIR}/${MODEL_NAME}")
add_test(NAME test-download-model COMMAND ${CMAKE_COMMAND}
-DDEST=${MODEL_DEST}
-DNAME=${MODEL_NAME}
-DHASH=${MODEL_HASH}
-P ${PROJECT_SOURCE_DIR}/cmake/download-models.cmake
)
set_tests_properties(test-download-model PROPERTIES FIXTURES_SETUP test-download-model)
llama_build_and_test(test-thread-safety.cpp ARGS -m "${MODEL_DEST}" -ngl 99 -p "The meaning of life is" -n 128 -c 256 -ub 32 -np 4 -t 2)
set_tests_properties(test-thread-safety PROPERTIES FIXTURES_REQUIRED test-download-model)
llama_build_and_test(test-arg-parser.cpp)
llama_build_and_test(test-model-resolution.cpp)
# the test serves its repos from an httplib server, and the library links it privately
target_link_libraries(test-model-resolution PRIVATE cpp-httplib)
if (NOT LLAMA_SANITIZE_ADDRESS AND NOT GGML_SCHED_NO_REALLOC)
# TODO: repair known memory leaks
llama_build_and_test(test-opt.cpp)
endif()
# TODO: make this test (and others) not link `libllama` as it is not needed [TAG_TESTS_LLAMA_LINK]
llama_build(test-backend-ops.cpp)
llama_build_and_test(test-tiled-mulmat.cpp)
llama_build_and_test(test-model-load-cancel.cpp LABEL "model")
llama_build_and_test(test-autorelease.cpp LABEL "model")
llama_build_and_test(test-backend-sampler.cpp LABEL "model")
# Test for state restore with fragmented KV cache
# Requires a model, uses same args pattern as test-thread-safety
llama_build_and_test(test-state-restore-fragmented.cpp LABEL "model" ARGS -m "${MODEL_DEST}")
set_tests_properties(test-state-restore-fragmented PROPERTIES FIXTURES_REQUIRED test-download-model)
if (APPLE)
llama_build(test-rset-release.cpp)
endif()
if (NOT GGML_BACKEND_DL AND GGML_CPU)
# these tests use the backends directly and cannot be built with dynamic loading
llama_build_and_test(test-barrier.cpp)
llama_build_and_test(test-quantize-fns.cpp)
llama_build_and_test(test-quantize-perf.cpp)
llama_build_and_test(test-rope.cpp)
llama_build_and_test(test-col2im-1d.cpp)
endif()
# libmtmd
set(LLAMA_TEST_NAME test-mtmd-c-api)
llama_build_and_test(test-mtmd-c-api.c)
target_link_libraries(${LLAMA_TEST_NAME} PRIVATE mtmd)
unset(LLAMA_TEST_NAME)
llama_build_and_test(test-mtmd-impl.cpp)
target_link_libraries(test-mtmd-impl PRIVATE mtmd)
# GGUF model data fetcher library for tests that need real model metadata
# Only compile when cpp-httplib has SSL support (CPPHTTPLIB_OPENSSL_SUPPORT)
if (TARGET cpp-httplib)
get_target_property(_cpp_httplib_defs cpp-httplib INTERFACE_COMPILE_DEFINITIONS)
if (_cpp_httplib_defs MATCHES "CPPHTTPLIB_OPENSSL_SUPPORT")
add_library(gguf-model-data STATIC gguf-model-data.cpp)
target_link_libraries(gguf-model-data PRIVATE llama-common cpp-httplib)
target_include_directories(gguf-model-data PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
add_executable(test-gguf-model-data test-gguf-model-data.cpp)
target_link_libraries(test-gguf-model-data PRIVATE gguf-model-data llama-common)
llama_test(test-gguf-model-data LABEL "model")
# test-quant-type-selection requires gguf-model-data for remote model metadata
llama_build_and_test(test-quant-type-selection.cpp LABEL "model")
target_link_libraries(test-quant-type-selection PRIVATE gguf-model-data)
target_compile_definitions(test-quant-type-selection PRIVATE
SNAPSHOT_DIR="${CMAKE_CURRENT_SOURCE_DIR}/snapshots")
endif()
endif()
# dummy executable - not installed
get_filename_component(TEST_TARGET test-c.c NAME_WE)
add_executable(${TEST_TARGET} test-c.c)
target_link_libraries(${TEST_TARGET} PRIVATE llama)
if (NOT LLAMA_USE_SYSTEM_GGML)
# Needs non-public ggml-impl.h
llama_build_and_test(test-gguf.cpp)
# Needs non-public ggml{,-backend}-impl.h
llama_build_and_test(test-alloc.cpp)
endif()
llama_build(test-export-graph-ops.cpp)
if (TARGET gguf-model-data)
target_link_libraries(test-export-graph-ops PRIVATE gguf-model-data)
target_compile_definitions(test-export-graph-ops PRIVATE LLAMA_HF_FETCH)
endif()
Reference in New Issue View Git Blame Copy Permalink