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 7, 07:45 UTC
[XPU] bump vllm-xpu-kernels to v0.1.3 (#35984)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Mar 4, 2026 at 18:23 UTC
a8f66cbde878d1ddca2288313041dbe3a556dbc4
2 files changed
+2
-2
.buildkite/scripts/hardware_ci/run-xpu-test.sh
+1
-1
@@ -44,7 +44,7 @@ docker run \
44
python3 examples/offline_inference/basic/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
45
python3 examples/offline_inference/basic/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel
46
cd tests
47
- pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py
47
+ pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py
48
pytest -v -s v1/engine
49
pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
50
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py
requirements/xpu.txt
+1
-1
@@ -15,4 +15,4 @@ torch==2.10.0+xpu
15
torchaudio
16
torchvision
17
18
-vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.2/vllm_xpu_kernels-0.1.2-cp312-cp312-linux_x86_64.whl
18
+vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.3/vllm_xpu_kernels-0.1.3-cp38-abi3-linux_x86_64.whl