ClaudeBot/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

ci : run test-backend-ops as a dedicated ci/run.sh test (#28740)

Browse Source 
* ci : run test-backend-ops as a dedicated gg test

Run test-backend-ops as a separate gg test in ci/run.sh so it is executed outside ctest. With GG_BUILD_HIGH_PERF it keeps the existing CPU-only invocation (-b CPU); otherwise it runs all available backends without a backend filter.

Remove the dedicated backend-ops workflow and keep test-backend-ops as a built target that is not registered with ctest to avoid duplicate runs.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* ci : run test-backend-ops earlier and enable high-perf on kleidiai

Move the test-backend-ops gg test before test-llama-archs.

Enable GG_BUILD_HIGH_PERF and LLAMA_ARG_THREADS on the Graviton4 KleidiAI job and use the standard self-hosted results/mnt paths.

Add TODO markers for decoupling tests from libllama.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* ci : run test-backend-ops in parallel

Pass -j $(nproc) to test-backend-ops in both high-perf and all-backend modes.

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* ci : disable parallel tests for ROCm

* cont : disable parallel tests with MoltenVK
This commit is contained in:
Georgi Gerganov
2026-09-11 22:00:57 +03:00
committed by GitHub
parent 982937a333
commit b78a39a2f9
6 changed files with 41 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ci/run.sh
+27 -11
View File
@@ -190,7 +190,7 @@ if [ ! -z ${GG_BUILD_OPENVINO} ]; then
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_OPENVINO=ON"
# TODO: fix failing tests on OpenVINO backend
CTEST_EXTRA="-E test-llama-archs|^test-recurrent-state-|test-backend-ops|test-save-load-state"
CTEST_EXTRA="-E test-llama-archs|^test-recurrent-state-|test-save-load-state"
fi
## helpers
@@ -250,7 +250,7 @@ function gg_run_ctest_debug {
(cmake -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Debug ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time cmake --build . --config Debug -j$(nproc)) 2>&1 | tee -a $OUT/${ci}-make.log
(time ctest -C Debug --output-on-failure -L main -E "test-opt|test-backend-ops|test-llama-archs" ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log
(time ctest -C Debug --output-on-failure -L main -E "test-opt|test-llama-archs" ${CTEST_EXTRA}) 2>&1 | tee -a $OUT/${ci}-ctest.log
set +e
}
@@ -768,25 +768,43 @@ function gg_check_build_requirements {
fi
}
function gg_run_test_backend_ops_cpu {
function gg_run_test_backend_ops {
cd ${SRC}
cd build-ci-release
set -e
(time ./bin/test-backend-ops -b CPU ) 2>&1 | tee -a $OUT/${ci}-test-backend-ops-cpu.log
local args_extra="-j $(nproc)"
# TODO: fix multi-threaded for ROCm
# https://github.com/ggml-org/llama.cpp/actions/runs/34576278519/job/103297889044?pr=28740#step:3:4865
if [ ! -z ${GG_BUILD_ROCM} ]; then
args_extra=""
fi
# TODO: MoltenVK bug?
# https://github.com/ggml-org/llama.cpp/actions/runs/34611260059/job/103302413736?pr=28740#step:3:5897
if [ ! -z "${GG_BUILD_VULKAN}" ] && [ "$(uname -s)" = "Darwin" ]; then
args_extra=""
fi
if [ ! -z ${GG_BUILD_HIGH_PERF} ]; then
(time ./bin/test-backend-ops ${args_extra} -b CPU) 2>&1 | tee -a $OUT/${ci}-test-backend-ops.log
else
(time ./bin/test-backend-ops ${args_extra} ) 2>&1 | tee -a $OUT/${ci}-test-backend-ops.log
fi
set +e
}
function gg_sum_test_backend_ops_cpu {
function gg_sum_test_backend_ops {
gg_printf '### %s\n\n' "${ci}"
gg_printf 'Runs test-backend-ops for CPU backend\n'
gg_printf 'Runs test-backend-ops\n'
gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
gg_printf '```\n'
gg_printf '%s\n' "$(cat $OUT/${ci}-test-backend-ops-cpu.log)"
gg_printf '%s\n' "$(cat $OUT/${ci}-test-backend-ops.log)"
gg_printf '```\n'
gg_printf '\n'
}
@@ -819,13 +837,11 @@ ret=0
test $ret -eq 0 && gg_run ctest_debug
test $ret -eq 0 && gg_run ctest_release
test $ret -eq 0 && gg_run test_backend_ops
test $ret -eq 0 && gg_run test_llama_archs_models
test $ret -eq 0 && gg_run test_llama_archs_tensor_split
if [ ! -z ${GG_BUILD_HIGH_PERF} ]; then
test $ret -eq 0 && gg_run test_backend_ops_cpu
fi
if [ -z ${GG_BUILD_LOW_PERF} ]; then
test $ret -eq 0 && gg_run embd_bge_small
test $ret -eq 0 && gg_run rerank_tiny