From f00c9083b2003ae888d8376b9f56ff94512ce9cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sigbj=C3=B8rn=20Skj=C3=A6ret?= Date: Fri, 23 Oct 2026 14:53:44 +0200 Subject: [PATCH] ci : add behavior check workflow (#31036) * remove python from tests * add behavior and backend ctest labels * add behavior check workflow [no ci] --- .github/workflows/behavior-check.yml | 109 +++++++++++++++++++++ .github/workflows/build-cpu.yml | 2 +- ci/run.sh | 2 +- tests/CMakeLists.txt | 138 ++++++++++++++------------- 4 files changed, 181 insertions(+), 70 deletions(-) create mode 100644 .github/workflows/behavior-check.yml diff --git a/.github/workflows/behavior-check.yml b/.github/workflows/behavior-check.yml new file mode 100644 index 000000000..22d8d7034 --- /dev/null +++ b/.github/workflows/behavior-check.yml @@ -0,0 +1,109 @@ +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', + ] + + pull_request: + types: [opened, synchronize, reopened] + paths: [ + '.github/workflows/behavior-check.yml', + '**/CMakeLists.txt', + '**/.cmake', + '**/*.h', + '**/*.hpp', + '**/*.c', + '**/*.cpp' + ] + +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 jinja2==3.1.6 + + - 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: ${{ secrets.HF_TOKEN_CACHE_OUTPUT }} + with: + key: behavior-check-ubuntu-26.04-arm + folder: llama.cpp + evict-old-files: 1d + hf_bucket: ggml-org/cache + save: true + + - name: Test + id: cmake_test + run: | + source .venv/bin/activate + cd build + ctest -L behavior -LE 'model|backend' --verbose --timeout 900 diff --git a/.github/workflows/build-cpu.yml b/.github/workflows/build-cpu.yml index 78d1c5f82..76a030e67 100644 --- a/.github/workflows/build-cpu.yml +++ b/.github/workflows/build-cpu.yml @@ -129,7 +129,7 @@ jobs: id: cmake_test run: | cd build - ctest -L 'main|python' --verbose --timeout 900 + ctest -L main --verbose --timeout 900 - name: Test llama2c conversion id: llama2c_test diff --git a/ci/run.sh b/ci/run.sh index bf6611fd0..e3ffdb8af 100755 --- a/ci/run.sh +++ b/ci/run.sh @@ -254,7 +254,7 @@ function gg_run_ctest_release { (time cmake --build . --config Release -j$(nproc)) 2>&1 | tee -a $OUT/${ci}-make.log if [ -z ${GG_BUILD_LOW_PERF} ]; then - (time ctest -C Release --output-on-failure -L 'main|python' ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log + (time ctest -C Release --output-on-failure -L main ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log else (time ctest -C Release --output-on-failure -L main -E test-opt ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log fi diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 815cc15a3..763154972 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -137,33 +137,34 @@ 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 --check-decode) -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) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-bert-bge.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-command-r.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-coder LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-coder.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-llm LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-llm.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-falcon LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-gemma-4 LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gemma-4.gguf --check-decode) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3 LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-phi-3.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen2.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen35 LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-qwen35.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder LABEL behavior 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 + LABEL behavior 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) + llama_build_and_test(test-grammar-llguidance.cpp LABEL "main behavior" ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf) endif () # llama_context state tests: KV and recurrent state save, load, copy, rollback @@ -180,20 +181,20 @@ llama_build(${LLAMA_CONTEXT_TEST_SRC}) 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 LINK llama) - llama_build_and_test(test-sampling.cpp LINK llama) - llama_build_and_test(test-reasoning-budget.cpp) - llama_build_and_test(test-grammar-parser.cpp LINK llama) - llama_build_and_test(test-grammar-integration.cpp) - llama_build_and_test(test-llama-grammar.cpp LINK llama) - llama_build_and_test(test-batch-alloc.cpp LINK llama) - llama_build_and_test(test-chat.cpp WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}) + llama_build_and_test(test-unicode.cpp LABEL behavior LINK llama) + llama_build_and_test(test-sampling.cpp LABEL behavior LINK llama) + llama_build_and_test(test-reasoning-budget.cpp LABEL behavior) + llama_build_and_test(test-grammar-parser.cpp LABEL behavior LINK llama) + llama_build_and_test(test-grammar-integration.cpp LABEL behavior) + llama_build_and_test(test-llama-grammar.cpp LABEL behavior LINK llama) + llama_build_and_test(test-batch-alloc.cpp LABEL behavior LINK llama) + llama_build_and_test(test-chat.cpp LABEL behavior 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-server-component.cpp) + llama_build_and_test(test-server-component.cpp LABEL behavior) target_include_directories(test-server-component PRIVATE ${PROJECT_SOURCE_DIR}/tools/server) target_link_libraries(test-server-component PRIVATE server-context) - llama_build_and_test(test-json-schema-to-grammar.cpp) + llama_build_and_test(test-json-schema-to-grammar.cpp LABEL behavior) if (NOT GGML_BACKEND_DL) llama_build(test-quantize-stats.cpp) @@ -205,20 +206,20 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS) 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) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-aquila LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-aquila.gguf) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-falcon LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-2 LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-neox LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-neox.gguf) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-llama-bpe LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf --ignore-merges) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-mpt LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-mpt.gguf) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-refact LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-refact.gguf) + #llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-starcoder LABEL behavior 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_test(test-tokenizer-1-spm NAME test-tokenizer-1-llama-spm LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf) + #llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-baichuan LABEL behavior ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-baichuan.gguf) # llama_build_and_test(test-double-float.cpp) # SLOW @@ -232,7 +233,7 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS) llama_test( test-llama-archs NAME test-generate-models - LABEL main + LABEL "main behavior backend" ARGS -o "${MODEL_DIR}" ) set_tests_properties(test-generate-models PROPERTIES @@ -242,7 +243,7 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS) # Test context state handling across all architectures, using the generated dummy models llama_test( test-llama-context - LABEL main + LABEL "main behavior backend" ARGS --models "${MODEL_DIR}" ) # abort on graph reallocations that the initial reserve should have covered @@ -254,15 +255,15 @@ if (NOT WIN32 OR NOT BUILD_SHARED_LIBS) 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) +llama_build_and_test(test-chat-peg-parser.cpp peg-parser/simple-tokenize.cpp LABEL behavior) +llama_build_and_test(test-jinja.cpp LABEL behavior) +llama_test(test-jinja NAME test-jinja-py ARGS -py LABEL "python behavior") +llama_build_and_test(test-json-schema.cpp LABEL behavior) +llama_build_and_test(test-chat-auto-parser.cpp LABEL behavior WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}) +llama_build_and_test(test-chat-template.cpp LABEL behavior) # 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-log.cpp LABEL behavior) llama_build_and_test( test-peg-parser.cpp peg-parser/simple-tokenize.cpp @@ -272,6 +273,7 @@ llama_build_and_test( peg-parser/test-python-dict-parser.cpp peg-parser/test-unicode.cpp peg-parser/tests.h + LABEL behavior ) if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "s390x") @@ -292,33 +294,33 @@ add_test(NAME test-download-model COMMAND ${CMAKE_COMMAND} set_tests_properties(test-download-model PROPERTIES FIXTURES_SETUP test-download-model) # the context state cases against a real model, the sweep above uses the generated dummy ones -llama_test(test-llama-context NAME test-llama-context-model LABEL "model" ARGS -m "${MODEL_DEST}") +llama_test(test-llama-context NAME test-llama-context-model LABEL "model behavior backend" ARGS -m "${MODEL_DEST}") set_tests_properties(test-llama-context-model PROPERTIES FIXTURES_REQUIRED test-download-model) -llama_build_and_test(test-thread-safety.cpp ARGS -m "${MODEL_DEST}" -ngl 99 -p "The meaning of life is" -n 128 -c 256 -ub 32 -np 4 -t 2) +llama_build_and_test(test-thread-safety.cpp LABEL "main backend" 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) +llama_build_and_test(test-arg-parser.cpp LABEL behavior) +llama_build_and_test(test-model-resolution.cpp LABEL behavior) # 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 LINK ggml) + llama_build_and_test(test-opt.cpp LABEL "main behavior backend" LINK ggml) endif() if (GGML_METAL AND NOT GGML_BACKEND_DL) # calls the Metal backend's graph optimizer and fusion table directly - llama_build_and_test(test-metal-graph-optimize.cpp LINK ggml ggml-metal) + llama_build_and_test(test-metal-graph-optimize.cpp LABEL "main behavior backend" LINK ggml ggml-metal) target_include_directories(test-metal-graph-optimize PRIVATE ${PROJECT_SOURCE_DIR}/ggml/src ${PROJECT_SOURCE_DIR}/ggml/src/ggml-metal) endif() llama_build(test-backend-ops.cpp LINK ggml) -llama_build_and_test(test-tiled-mulmat.cpp LINK ggml) -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") +llama_build_and_test(test-tiled-mulmat.cpp LABEL "main behavior backend" LINK ggml) +llama_build_and_test(test-model-load-cancel.cpp LABEL "model behavior") +llama_build_and_test(test-autorelease.cpp LABEL "model behavior") +llama_build_and_test(test-backend-sampler.cpp LABEL "model behavior backend") if (APPLE) llama_build(test-rset-release.cpp) @@ -326,19 +328,19 @@ 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 LINK ggml) - llama_build_and_test(test-quantize-fns.cpp LINK ggml) - llama_build_and_test(test-quantize-perf.cpp LINK ggml) - llama_build_and_test(test-rope.cpp LINK ggml) - llama_build_and_test(test-col2im-1d.cpp LINK ggml) - llama_build_and_test(test-conv-1d.cpp LINK ggml) - llama_build_and_test(test-gelu-quick.cpp LINK ggml) + llama_build_and_test(test-barrier.cpp LABEL "main behavior" LINK ggml) + llama_build_and_test(test-quantize-fns.cpp LABEL "main behavior" LINK ggml) + llama_build_and_test(test-quantize-perf.cpp LABEL "main behavior backend" LINK ggml) + llama_build_and_test(test-rope.cpp LABEL "main behavior backend" LINK ggml) + llama_build_and_test(test-col2im-1d.cpp LABEL "main behavior backend" LINK ggml) + llama_build_and_test(test-conv-1d.cpp LABEL "main behavior backend" LINK ggml) + llama_build_and_test(test-gelu-quick.cpp LABEL "main behavior backend" LINK ggml) endif() # libmtmd -llama_build_and_test(test-mtmd-c-api.c LINK mtmd) +llama_build_and_test(test-mtmd-c-api.c LABEL behavior LINK mtmd) -llama_build_and_test(test-mtmd-impl.cpp LINK mtmd) +llama_build_and_test(test-mtmd-impl.cpp LABEL behavior LINK mtmd) # GGUF model data fetcher library for tests that need real model metadata # Only compile when cpp-httplib has SSL support (CPPHTTPLIB_OPENSSL_SUPPORT) @@ -351,10 +353,10 @@ if (TARGET cpp-httplib) 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") + llama_test(test-gguf-model-data LABEL "model behavior") # test-quant-type-selection requires gguf-model-data for remote model metadata - llama_build_and_test(test-quant-type-selection.cpp LABEL "model" LINK llama) + llama_build_and_test(test-quant-type-selection.cpp LABEL "model behavior" LINK llama) 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") @@ -368,10 +370,10 @@ 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 LINK ggml) + llama_build_and_test(test-gguf.cpp LABEL behavior LINK ggml) # Needs non-public ggml{,-backend}-impl.h - llama_build_and_test(test-alloc.cpp LINK ggml) + llama_build_and_test(test-alloc.cpp LABEL "behavior backend" LINK ggml) endif() llama_build(test-export-graph-ops.cpp)