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

[XPU] skip unsupported ut and update test_nixl_connector (#37179)

Browse Source 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
liuzhenwei
2026-03-18 13:32:59 +08:00
committed by GitHub
parent 0e95916155
commit 86b7e3c95a
2 changed files with 10 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.buildkite/scripts/hardware_ci/run-xpu-test.sh
View File

@@ -40,16 +40,16 @@ docker run \
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8 python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel
cd tests cd tests
pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py
pytest -v -s v1/engine pytest -v -s v1/engine
pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py
pytest -v -s v1/structured_output pytest -v -s v1/structured_output
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 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
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 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 -k "not (test_register_kv_caches and FLASH_ATTN and True)"
pytest -v -s v1/test_serial_utils.py pytest -v -s v1/test_serial_utils.py
' '

8
tests/v1/kv_connector/unit/test_nixl_connector.py
View File

@@ -1369,7 +1369,13 @@ def test_abort_timeout_on_prefiller(monkeypatch, distributed_executor_backend):
"NIXL_TELEMETRY_ENABLE": "1", "NIXL_TELEMETRY_ENABLE": "1",
}, },
} }
ray.init(runtime_env=runtime_env) # On XPU/ROCm, vLLM expects Ray's device key to be "GPU".
# Explicitly reserving GPU resources here prevents false negatives
# when Ray cannot auto-detect accelerator resources in test envs.
ray_init_kwargs: dict[str, Any] = {"runtime_env": runtime_env}
if not current_platform.is_cuda():
ray_init_kwargs["num_gpus"] = 1
ray.init(**ray_init_kwargs)
try: try:
run_test_and_cleanup() run_test_and_cleanup()
finally: finally: