A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 06:00 UTC
[BugFix][CPU] Fix CPU CI by ignore collecting test_pixtral (#19411)
Signed-off-by: jiang.li <jiang1.li@intel.com>
Li, Jiang committed
Jun 10, 2025 at 20:02 UTC
e4248849ec1dea54851a1d1769c86e1504f183ea
1 file changed
+4
-1
.buildkite/scripts/hardware_ci/run-cpu-test.sh
+4
-1
@@ -43,7 +43,10 @@ function cpu_tests() {
43
pytest -v -s tests/kernels/attention/test_mla_decode_cpu.py -m cpu_model
44
pytest -v -s tests/models/language/generation -m cpu_model
45
pytest -v -s tests/models/language/pooling -m cpu_model
46
- pytest -v -s tests/models/multimodal/generation --ignore=tests/models/multimodal/generation/test_mllama.py -m cpu_model"
46
+ pytest -v -s tests/models/multimodal/generation \
47
+ --ignore=tests/models/multimodal/generation/test_mllama.py \
48
+ --ignore=tests/models/multimodal/generation/test_pixtral.py \
49
+ -m cpu_model"
50
51
# Run compressed-tensor test
52
docker exec cpu-test-"$NUMA_NODE" bash -c "