squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI/Build] Adding timeout in CPU CI to avoid CPU test queue blocking (#6892)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Li, Jiang 2024-11-09 11:27:11 +08:00 committed by GitHub
parent 127c07480e
commit d7edca1dee
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 79 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
.buildkite/run-cpu-test-ppc64le.sh
View File

@ -17,6 +17,7 @@ source /etc/environment
#docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test cpu-test
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --privileged=true --network host -e HF_TOKEN="$HF_TOKEN" --name cpu-test cpu-test
function cpu_tests() {
# Run basic model test
docker exec cpu-test bash -c "
set -e
@ -28,8 +29,7 @@ docker exec cpu-test bash -c "
# pytest -v -s tests/models/embedding/language
pytest -v -s tests/models/encoder_decoder/language
pytest -v -s tests/models/decoder_only/language/test_models.py
# Chunked prefill not supported for CPU yet
# pytest -v -s tests/models/decoder_only/audio_language -m cpu_model
pytest -v -s tests/models/decoder_only/audio_language -m cpu_model
pytest -v -s tests/models/decoder_only/vision_language -m cpu_model"
# online inference
@ -44,3 +44,8 @@ docker exec cpu-test bash -c "
--num-prompts 20 \
--endpoint /v1/completions \
--tokenizer facebook/opt-125m"
}
# All of CPU tests are expected to be finished less than 25 mins.
export -f cpu_tests
timeout 25m bash -c "cpu_tests"

9
.buildkite/run-cpu-test.sh
View File

@ -19,6 +19,7 @@ docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/hugg
docker run -itd --entrypoint /bin/bash -v ~/.cache/huggingface:/root/.cache/huggingface --cpuset-cpus=48-95 \
--cpuset-mems=1 --privileged=true --network host -e HF_TOKEN --env VLLM_CPU_KVCACHE_SPACE=4 --shm-size=4g --name cpu-test-avx2 cpu-test-avx2
function cpu_tests() {
# offline inference
docker exec cpu-test-avx2 bash -c "
set -e
@ -35,8 +36,7 @@ docker exec cpu-test bash -c "
# pytest -v -s tests/models/embedding/language
pytest -v -s tests/models/encoder_decoder/language
pytest -v -s tests/models/decoder_only/language/test_models.py
# Chunked prefill not supported for CPU yet
# pytest -v -s tests/models/decoder_only/audio_language -m cpu_model
pytest -v -s tests/models/decoder_only/audio_language -m cpu_model
pytest -v -s tests/models/decoder_only/vision_language -m cpu_model"
# Run compressed-tensor test
@ -66,3 +66,8 @@ docker exec cpu-test bash -c "
--num-prompts 20 \
--endpoint /v1/completions \
--tokenizer facebook/opt-125m"
}
# All of CPU tests are expected to be finished less than 25 mins.
export -f cpu_tests
timeout 25m bash -c "cpu_tests"