Skip to content

[Fix] Handle online FP8 quantization config for unquantized diffusion models #26261

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
yichiche wants to merge 4 commits into from
Closed

[Fix] Handle online FP8 quantization config for unquantized diffusion models #26261

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
472b94e
docs: sync LMSYS SGLang blog cards
github-actions[bot] May 7, 2026
09c8c9e
Merge branch 'sgl-project:main' into main
yichiche May 15, 2026
25688fc
Merge branch 'sgl-project:main' into main
yichiche May 20, 2026
93e01ee
[Fix] Handle online FP8 quantization config for unquantized diffusion…
yichiche May 25, 2026
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
6 changes: 5 additions & 1 deletion python/sglang/multimodal_gen/runtime/loader/transformer_load_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -497,7 +497,11 @@ def _resolve_quant_config(
return get_quant_config(hf_config, component_model_path)

quant_cls = get_quantization_config(server_args.quantization)
return quant_cls.from_config({})
try:
return quant_cls.from_config({})
except (ValueError, KeyError):
ignored = getattr(server_args, "quantization_ignored_layers", None)
Comment on lines +500 to +503

@ColinZ22 ColinZ22 May 26, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

All default values for online quantization are already set for all supported online quantization methods (mxfp4 and fp8), no need to add try catch, 1-line fix is sufficient as detailed here: #26415

@yichiche yichiche May 28, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

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

Hi @ColinZ22, thanks for the cleaner fix — agreed, quant_cls() is the right abstraction and generalizes to mxfp4, so it's strictly better than the FP8-only try/except here. I'll close this PR in favor of #26415.

return quant_cls(ignored_layers=ignored)

quant_config = get_quant_config(hf_config, component_model_path)
if quant_config is None and server_args.transformer_weights_path:
Expand Down
Loading