Skip to content

use group gemm nz #910

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ttanzhiqiang wants to merge 2 commits into from
+5 −0
Closed

use group gemm nz #910

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
52d067d
use group gemm nz
ttanzhiqiang May 20, 2025
5c8b2c0
Merge branch 'main' into group_gemm_nz
ttanzhiqiang Jun 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions vllm_ascend/quantization/w8a8_dynamic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -816,8 +816,13 @@
1, 2).contiguous()
layer.w2_weight.data = layer.w2_weight.data.transpose(
1, 2).contiguous()

torch_npu.npu_format_cast_(layer.w13_weight, 29)
torch_npu.npu_format_cast_(layer.w2_weight, 29)

Check warning on line 821 in vllm_ascend/quantization/w8a8_dynamic.py

View check run for this annotation

Codecov / codecov/patch

vllm_ascend/quantization/w8a8_dynamic.py#L820-L821 

Added lines #L820 - L821 were not covered by tests
Copy link
Copy Markdown
Collaborator

@linfeng-yuan linfeng-yuan May 23, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for contribution. The transformation of grouped_matmul may lead to accuracy problem until newer torch_npu releases. I think it is good to hang up this PR temporarily.


if envs.VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP:
torch_npu.npu_format_cast_(layer.w2_weight, ACL_FORMAT_FRACTAL_NZ)

layer.w13_weight_scale.data = layer.w13_weight_scale.data.view(
layer.w13_weight_scale.data.shape[0], -1)
layer.w13_weight_offset.data = layer.w13_weight_offset.data.view(
Expand Down
Loading