[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>
zofia committed
Aug 11, 2026 at 16:43 UTC
52c70b210ce9d66e9afb9d18e086c3d05408c492
2 files changed
+2
.buildkite/intel_jobs/test-intel.yaml
+1
@@ -72,6 +72,7 @@ steps:
72
'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 &&
73
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 &&
74
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 &&
75
+ python3 examples/basic/offline_inference/generate.py --linear-backend torch --model Qwen/Qwen3-4B-Instruct-2507-FP8 --enforce-eager --max-model-len 4096 &&
76
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 &&
77
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
78
'
vllm/model_executor/kernels/linear/__init__.py
+1
@@ -426,6 +426,7 @@ _POSSIBLE_FP8_BLOCK_KERNELS: dict[
426
PlatformEnum.XPU: [
427
XPUFp8BlockScaledMMKernel,
428
TritonFp8BlockScaledMMKernel,
429
+ BlockWiseTorchFP8ScaledMMLinearKernel,
430
],
431
}
432