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 4, 02:30 UTC
[CI][XPU] Skip fork-dependent logits processor test (#42013)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
liuzhenwei committed
May 8, 2026 at 21:10 UTC
f2bbd575e2be8d901f65e304fcedd05ca7afa31a
1 file changed
+1
-1
.buildkite/intel_jobs/misc_intel.yaml
+1
-1
@@ -49,7 +49,7 @@ steps:
49
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
50
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
51
cd tests &&
52
- pytest -v -s v1/logits_processors &&
52
+ pytest -v -s v1/logits_processors --ignore=v1/logits_processors/test_custom_online.py --ignore=v1/logits_processors/test_custom_offline.py &&
53
pytest -v -s v1/test_oracle.py &&
54
pytest -v -s v1/test_request.py &&
55
pytest -v -s v1/test_outputs.py'