biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build][CPU] Fix CPU CI and remove all CPU V0 files (#20560)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2025-07-08 13:13:44 +08:00
committed by GitHub
parent 8369b7c2a9
commit 7721ef1786
9 changed files with 785 additions and 839 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
.buildkite/scripts/hardware_ci/run-cpu-test.sh
View File

@@ -48,10 +48,16 @@ function cpu_tests() {
# Run basic model test
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -v -s tests/kernels/attention/test_cache.py -m cpu_model
pytest -v -s tests/kernels/attention/test_mla_decode_cpu.py -m cpu_model
pytest -v -s tests/models/language/generation -m cpu_model
VLLM_CPU_SGL_KERNEL=1 pytest -v -s tests/models/language/generation -m cpu_model
# Note: disable until supports V1
# pytest -v -s tests/kernels/attention/test_cache.py -m cpu_model
# pytest -v -s tests/kernels/attention/test_mla_decode_cpu.py -m cpu_model
# Note: disable Bart until supports V1
pytest -v -s tests/models/language/generation -m cpu_model \
--ignore=tests/models/language/generation/test_bart.py
VLLM_CPU_SGL_KERNEL=1 pytest -v -s tests/models/language/generation -m cpu_model \
--ignore=tests/models/language/generation/test_bart.py
pytest -v -s tests/models/language/pooling -m cpu_model
pytest -v -s tests/models/multimodal/generation \
--ignore=tests/models/multimodal/generation/test_mllama.py \
@@ -62,21 +68,15 @@ function cpu_tests() {
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v \
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_static_setup \
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]"
# Note: disable it until supports V1
# Run AWQ test
# docker exec cpu-test-"$NUMA_NODE" bash -c "
# set -e
# VLLM_USE_V1=0 pytest -s -v \
# tests/quantization/test_ipex_quant.py"
# Run chunked-prefill and prefix-cache test
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
pytest -s -v -k cpu_model \
tests/basic_correctness/test_chunked_prefill.py"
# online serving
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e