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 13, 05:45 UTC
[XPU][CI]disable lm cache uts (#28696)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Nov 14, 2025 at 11:15 UTC
da14ae0fad3165b88fcdc03a8f59f1813f8e832a
1 file changed
+1
-1
.buildkite/scripts/hardware_ci/run-xpu-test.sh
+1
-1
@@ -46,6 +46,6 @@ docker run \
46
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py
47
pytest -v -s v1/structured_output
48
pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_tree_attention.py --ignore=v1/spec_decode/test_speculators_eagle3.py
49
- pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py --ignore=v1/kv_connector/unit/test_shared_storage_connector.py
49
+ pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py --ignore=v1/kv_connector/unit/test_shared_storage_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py
50
pytest -v -s v1/test_serial_utils.py
51
'