support modelopt W4A16 NVFP4 export for grouped MoE weights#4566
Open
HollowMan6 wants to merge 1 commit into
Open
support modelopt W4A16 NVFP4 export for grouped MoE weights#4566HollowMan6 wants to merge 1 commit into
HollowMan6 wants to merge 1 commit into
Conversation
- Extend AutoBridge.export_hf_weights_modelopt to support quant_mode="w4a16_nvfp4".
- Collect ModelOpt quant metadata from the actual quantized weight/module, including NVFP4 weight_scale_2.
- Map Megatron ModelOpt metadata onto exported HF names before quantization.
- Support grouped MoE expert exports by syncing EP metadata, stacking per-expert metadata, and emitting vLLM ModelOpt fused-MoE tensor names:
- *.experts.w13_weight
- *.experts.w13_weight_scale
- *.experts.w13_weight_scale_2
- *.experts.w2_weight
- *.experts.w2_weight_scale
- *.experts.w2_weight_scale_2
- Keep ignored weights unquantized and skip quantizer tensors during export.
Signed-off-by: Hollow Man <hollowman@opensuse.org>
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do ?
Support modelopt W4A16 NVFP4 export for grouped MoE weights
Changelog
GitHub Actions CI
See the CI section in the Contributing doc for how to trigger the CI. A Nvidia developer will need to approve and trigger the CI for external contributors.
Before your PR is "Ready for review"
Pre checks:
If you haven't finished some of the above items you can still open "Draft" PR.
Additional Information