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 6, 09:30 UTC
[XPU] bump vllm-xpu-kernels to v0.1.4 (#37641)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Mar 20, 2026 at 15:04 UTC
bdf6a0a57bfed4f4fee29a10ed066d8c0d427883
1 file changed
+1
-1
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/v0.1.3/vllm_xpu_kernels-0.1.3-cp38-abi3-linux_x86_64.whl
18
+vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.4/vllm_xpu_kernels-0.1.4-cp38-abi3-manylinux_2_28_x86_64.whl