[Quantization][INC][ARK] Support INT2 XPU WOQ Linear (#47521)

Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com>
Signed-off-by: Zhenzhong Xu <zhenzhong.xu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Zhenzhong Xu
2026-07-14 08:29:45 +08:00
committed by GitHub
co-authored by Kunshang Ji
parent 21472f32ea
commit 0b0ef8d7eb
3 changed files with 158 additions and 5 deletions
+1 -1
View File
@@ -17,5 +17,5 @@ torchaudio
torchvision
torchcodec >= 0.14 # Required for the torchcodec video decoding backend
auto_round_lib>=0.14.0
auto_round_lib==0.14.1
vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.11/vllm_xpu_kernels-0.1.11-cp38-abi3-manylinux_2_28_x86_64.whl