[XPU] [Linear] enable torch linear backend for blockwise gemm on xpu (#50826)

Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
zofia
2026-08-11 16:43:33 +08:00
committed by GitHub
co-authored by Kunshang Ji
parent 529d010351
commit 52c70b210c
2 changed files with 2 additions and 0 deletions
+1
View File
@@ -72,6 +72,7 @@ steps:
'python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 &&
python3 examples/basic/offline_inference/generate.py --linear-backend torch --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 &&
python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic --enforce-eager --max-model-len 4096 &&
python3 examples/basic/offline_inference/generate.py --linear-backend torch --model Qwen/Qwen3-4B-Instruct-2507-FP8 --enforce-eager --max-model-len 4096 &&
python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8 --enforce-eager --max-model-len 4096 &&
python3 examples/basic/offline_inference/generate.py --linear-backend torch --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8 --enforce-eager --max-model-len 4096
'
@@ -426,6 +426,7 @@ _POSSIBLE_FP8_BLOCK_KERNELS: dict[
PlatformEnum.XPU: [
XPUFp8BlockScaledMMKernel,
TritonFp8BlockScaledMMKernel,
BlockWiseTorchFP8ScaledMMLinearKernel,
],
}