[Bugfix] Fix gpt-oss w4a8 DP/EP on B200 (#26729)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com> Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Varun Sundar Rabindranath
Michael Goin
parent
f95da13c3d
commit
5ff5d94e77
@@ -18,4 +18,7 @@ def mxfp8_e4m3_quantize(x: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
|
||||
"`pip install flashinfer`"
|
||||
) from err
|
||||
|
||||
return mxfp8_e4m3_quantize(x, is_sf_swizzled_layout=False)
|
||||
x_q, x_scales = mxfp8_e4m3_quantize(x, is_sf_swizzled_layout=False)
|
||||
if x_scales.ndim == 1:
|
||||
x_scales = x_scales.view(x.size(0), -1)
|
||||
return x_q, x_scales
|
||||
|
||||
Reference in New Issue
Block a user