Skip to content

Reintroduce memory usage fix #9535

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

Merged
zhyncs merged 1 commit into from
Aug 25, 2025
Merged

Reintroduce memory usage fix #9535

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions python/sglang/srt/layers/quantization/modelopt_quant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1212,11 +1212,13 @@ def process_weights_after_loading(self, layer: torch.nn.Module) -> None:

# Process w13 weights
w13_blockscale_swizzled = self.swizzle_blockscale(layer.w13_weight_scale)
del layer.w13_weight_scale
layer.w13_blockscale_swizzled.data.copy_(w13_blockscale_swizzled)
layer.w13_weight = Parameter(layer.w13_weight.data, requires_grad=False)

# Process w2 weights
w2_blockscale_swizzled = self.swizzle_blockscale(layer.w2_weight_scale)
del layer.w2_weight_scale
layer.w2_blockscale_swizzled.data.copy_(w2_blockscale_swizzled)
layer.w2_weight = Parameter(layer.w2_weight.data, requires_grad=False)

Expand Down
Loading