CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ci: run the x64 and arm ci on the github machines instead (#16183)

Browse Source 
* run the x64 ci on regular machines

* set up the same thing for arm

fix test-quantize-perf just like #12306

* try to disable sve

* add another sve run
This commit is contained in:
Eve
2025-09-25 05:06:06 +00:00
committed by GitHub
parent 5fb557653b
commit bee378e098
3 changed files with 98 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
.github/workflows/build.yml vendored
View File

@@ -1251,56 +1251,129 @@ jobs:
# TODO: simplify the following workflows using a matrix
# TODO: run lighter CI on PRs and the full CI only on master (if needed)
ggml-ci-x64-cpu-low-perf:
runs-on: [self-hosted, Linux, X64, CPU, low-perf]
runs-on: ubuntu-22.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ggml-ci-x64-cpu-low-perf
evict-old-files: 1d
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libcurl4-openssl-dev
- name: Test
id: ggml-ci
run: |
bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-arm64-cpu-low-perf:
runs-on: [self-hosted, Linux, ARM64, CPU, low-perf]
runs-on: ubuntu-22.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ggml-ci-arm64-cpu-low-perf
evict-old-files: 1d
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libcurl4-openssl-dev
- name: Test
id: ggml-ci
run: |
bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_LOW_PERF=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-x64-cpu-high-perf:
runs-on: [self-hosted, Linux, X64, CPU, high-perf]
runs-on: ubuntu-22.04
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ggml-ci-x64-cpu-high-perf
evict-old-files: 1d
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libcurl4-openssl-dev
- name: Test
id: ggml-ci
run: |
bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
LLAMA_ARG_THREADS=$(nproc) bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-arm64-cpu-high-perf:
runs-on: [self-hosted, Linux, ARM64, CPU, high-perf]
runs-on: ubuntu-22.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ggml-ci-arm64-cpu-high-perf
evict-old-files: 1d
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libcurl4-openssl-dev
- name: Test
id: ggml-ci
run: |
GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_SVE=1 GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-arm64-cpu-high-perf-sve:
runs-on: ubuntu-22.04-arm
steps:
- name: Clone
id: checkout
uses: actions/checkout@v4
- name: ccache
uses: ggml-org/ccache-action@v1.2.16
with:
key: ggml-ci-arm64-cpu-high-perf-sve
evict-old-files: 1d
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get install build-essential libcurl4-openssl-dev
- name: Test
id: ggml-ci
run: |
LLAMA_ARG_THREADS=$(nproc) GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ./tmp/results ./tmp/mnt
ggml-ci-x64-nvidia-cuda:
runs-on: [self-hosted, Linux, X64, NVIDIA]

27
ci/run.sh
View File

@@ -109,6 +109,11 @@ if [ ! -z ${GG_BUILD_MUSA} ]; then
MUSA_ARCH=${MUSA_ARCH:-21}
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_MUSA=ON -DMUSA_ARCHITECTURES=${MUSA_ARCH}"
fi
if [ ! -z ${GG_BUILD_NO_SVE} ]; then
# arm 9 and newer enables sve by default, adjust these flags depending on the cpu used
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=armv8.5-a+fp16+i8mm"
fi
## helpers
# download a file if it does not exist or if it is outdated
@@ -345,16 +350,16 @@ function gg_run_qwen3_0_6b {
wiki_test="${path_wiki}/wiki.test.raw"
./bin/llama-quantize ${model_bf16} ${model_q8_0} q8_0
./bin/llama-quantize ${model_bf16} ${model_q4_0} q4_0
./bin/llama-quantize ${model_bf16} ${model_q4_1} q4_1
./bin/llama-quantize ${model_bf16} ${model_q5_0} q5_0
./bin/llama-quantize ${model_bf16} ${model_q5_1} q5_1
./bin/llama-quantize ${model_bf16} ${model_q2_k} q2_k
./bin/llama-quantize ${model_bf16} ${model_q3_k} q3_k
./bin/llama-quantize ${model_bf16} ${model_q4_k} q4_k
./bin/llama-quantize ${model_bf16} ${model_q5_k} q5_k
./bin/llama-quantize ${model_bf16} ${model_q6_k} q6_k
./bin/llama-quantize ${model_bf16} ${model_q8_0} q8_0 $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q4_0} q4_0 $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q4_1} q4_1 $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q5_0} q5_0 $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q5_1} q5_1 $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q2_k} q2_k $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q3_k} q3_k $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q4_k} q4_k $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q5_k} q5_k $(nproc)
./bin/llama-quantize ${model_bf16} ${model_q6_k} q6_k $(nproc)
(time ./bin/llama-cli -no-cnv --model ${model_f16} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log
(time ./bin/llama-cli -no-cnv --model ${model_bf16} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log
@@ -427,7 +432,7 @@ function gg_run_qwen3_0_6b {
function gg_sum_qwen3_0_6b {
gg_printf '### %s\n\n' "${ci}"
gg_printf 'Pythia 2.8B:\n'
gg_printf 'Qwen3 0.6B:\n'
gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
gg_printf '- perplexity:\n%s\n' "$(cat $OUT/${ci}-ppl.log)"
gg_printf '- imatrix:\n```\n%s\n```\n' "$(cat $OUT/${ci}-imatrix-sum.log)"

11
tests/test-quantize-perf.cpp
View File

@@ -260,14 +260,7 @@ int main(int argc, char * argv[]) {
int64_t iterations = params.iterations;
// Initialize GGML, ensures float conversion tables are initialized
struct ggml_init_params ggml_params = {
/* .mem_size = */ 1*1024,
/* .mem_buffer = */ NULL,
/* .no_alloc = */ true,
};
struct ggml_context * ctx = ggml_init(ggml_params);
ggml_cpu_init();
for (int i = 0; i < GGML_TYPE_COUNT; i++) {
ggml_type type = (ggml_type) i;
@@ -359,7 +352,5 @@ int main(int argc, char * argv[]) {
}
}
ggml_free(ctx);
return 0;
}