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 4, 15:00 UTC
[xpu] bump up vllm-xpu-kernel v0.1.7 (#41019)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Apr 28, 2026 at 08:04 UTC
407b34be263320f843c0251af64a8521760871ea
2 files changed
+1
-2
.buildkite/intel_jobs/lora_intel.yaml
-1
@@ -126,5 +126,4 @@ steps:
126
'cd tests &&
127
pytest -v -s lora/test_default_mm_loras.py &&
128
(pytest -v -s lora/test_qwen3_unembed.py || true) &&
129
- (pytest -v -s lora/test_qwenvl.py || true) &&
129
pytest -v -s lora/test_whisper.py'
requirements/xpu.txt
+1
-1
@@ -15,4 +15,4 @@ torch==2.11.0+xpu
15
torchaudio
16
torchvision
17
18
-vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.5/vllm_xpu_kernels-0.1.5-cp38-abi3-manylinux_2_28_x86_64.whl
18
+vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.7/vllm_xpu_kernels-0.1.7-cp38-abi3-manylinux_2_28_x86_64.whl