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 9, 11:15 UTC
[XPU]disable test_acceptance_length UT (#33226)
Yan Ma committed
Jan 28, 2026 at 15:24 UTC
9581185d5110f67c22c1e3e78b270a5a12029af3
1 file changed
+1
-1
.buildkite/scripts/hardware_ci/run-xpu-test.sh
+1
-1
@@ -46,7 +46,7 @@ docker run \
46
pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
47
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py
48
pytest -v -s v1/structured_output
49
- 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/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 --ignore=v1/spec_decode/test_acceptance_length.py
50
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_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py
51
pytest -v -s v1/test_serial_utils.py
52
'