Fix the E8M0 scale computation in the MXFP4 (W4A4) MOE CUTLASS kernel (#43557)
Signed-off-by: Xin He <xin3.he@intel.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Kunshang Ji
parent
b997071ec4
commit
5ed15f42b9
@@ -56,7 +56,7 @@ class FlashInferMxFp4LinearKernel(MxFp4LinearKernel):
|
||||
out_shape = x.shape[:-1] + (layer.output_size_per_partition,)
|
||||
x_2d = x.reshape(-1, x.shape[-1])
|
||||
|
||||
x_fp4, x_scale = flashinfer_mxfp4_quantize(x_2d)
|
||||
x_fp4, x_scale = flashinfer_mxfp4_quantize(x_2d.contiguous())
|
||||
out = flashinfer_scaled_fp4_mm(
|
||||
x_fp4,
|
||||
weight,
|
||||
|
||||
Reference in New Issue
Block a user