feat: add Hy3 support, MTP, and FP8 optimizations - #4815
Open
yidingcheng0206 wants to merge 21 commits into
Open
feat: add Hy3 support, MTP, and FP8 optimizations#4815yidingcheng0206 wants to merge 21 commits into
yidingcheng0206 wants to merge 21 commits into
Conversation
grimoire
reviewed
Aug 4, 2026
grimoire
reviewed
Aug 4, 2026
grimoire
reviewed
Aug 4, 2026
grimoire
reviewed
Aug 4, 2026
grimoire
reviewed
Aug 4, 2026
| main_stream = torch.cuda.current_stream( | ||
| hidden_states.device, | ||
| ) | ||
| shared_stream = _get_hy3_shared_expert_stream( |
Collaborator
There was a problem hiding this comment.
I can accept this for this PR. But this implementation is dirty and device related.
We should find a way to make this an engine feature so it can be used for different model/backend.
grimoire
reviewed
Aug 4, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Draft PR for Hy3 model support, embedded MTP speculative decoding, static FP8 support, and opt-in kernel optimizations. Detailed description and known issues will be added next.