[XPU][MXFP4] add mxfp4 quant op for XPU (#39857)

Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
This commit is contained in:
zofia
2026-04-15 12:28:19 +00:00
committed by GitHub
parent 68be0f853e
commit fc701c8058
2 changed files with 50 additions and 0 deletions
@@ -162,3 +162,7 @@ try:
quant_dequant_mxfp4 = torch.ops.vllm.quant_dequant_mxfp4
except AttributeError as error:
raise error
def xpu_mxfp4_quantize(x: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
return torch.ops.vllm.xpu_mxfp4_quantize(x)