[XPU] bump vllm-xpu-kernels to v0.1.3 (#35984)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
@@ -44,7 +44,7 @@ docker run \
|
|||||||
python3 examples/offline_inference/basic/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
|
python3 examples/offline_inference/basic/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2
|
||||||
python3 examples/offline_inference/basic/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel
|
python3 examples/offline_inference/basic/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
|
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
|
||||||
|
|||||||
@@ -15,4 +15,4 @@ torch==2.10.0+xpu
|
|||||||
torchaudio
|
torchaudio
|
||||||
torchvision
|
torchvision
|
||||||
|
|
||||||
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
|
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
|
||||||
|
|||||||
Reference in New Issue
Block a user