Skip to content

[WIP][RL] fix fp8 update weight #7421

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

[WIP][RL] fix fp8 update weight #7421

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c0ac34c
[RL] fix fp8 update weight
zhuzilin Jun 21, 2025
918d495
Merge branch 'main' into feature/fp8_update_weight
zhyncs 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
8 changes: 4 additions & 4 deletions python/sglang/srt/layers/quantization/fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,10 +332,10 @@ def process_weights_after_loading(self, layer: Module) -> None:
layer.input_scale = None
else:
weight, weight_scale = layer.weight.data, layer.weight_scale_inv.data
layer.weight = torch.nn.Parameter(weight, requires_grad=False)
layer.weight_scale_inv = torch.nn.Parameter(
weight_scale, requires_grad=False
)
# layer.weight = torch.nn.Parameter(weight, requires_grad=False)
# layer.weight_scale_inv = torch.nn.Parameter(
# weight_scale, requires_grad=False
# )
Comment on lines +335 to +338
Copy link

Choose a reason for hiding this comment

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

medium

Consider removing these commented-out lines to reduce code clutter and improve readability. If the code is intentionally commented out for debugging or future use, add a comment explaining the reason.

return

layer.weight = torch.nn.Parameter(layer.weight.data, requires_grad=False)
Expand Down