[XPU] add xpu backend implementation of mxfp8 quant (#38682)

Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
zofia
2026-04-08 08:30:35 +08:00
committed by GitHub
co-authored by Kunshang Ji
parent 70406eb1dc
commit ad3304425b
2 changed files with 54 additions and 0 deletions
@@ -205,6 +205,12 @@ direct_register_custom_op(
)
def xpu_mxfp8_quantize(
x: torch.Tensor, dtype: torch.dtype | None = None
) -> tuple[torch.Tensor, torch.Tensor]:
return torch.ops.vllm.xpu_mxfp8_quantize(x, dtype)
class Mxfp8LinearOp:
def __init__(self):
self.backend = select_mxfp8_linear_backend()