feat(deepseek_v4): 1. use rope_rotate_activation instead of rotary_em…#701
Merged
valarLip merged 1 commit intoMay 6, 2026
Conversation
junhaha666
commented
May 6, 2026
Contributor
- use rope_rotate_activation instead of rotary_emb + rotate_activation; related aiter pr add rope/rotate_activation/fp4_quant_inplace fused kernel for dsv4 aiter#3035
- use topk_softplus fused kernel; related aiter pr add topk_softplus kernel aiter#2995
- use mhc_pre in hc_head; related aiter pr Update mhc_pre hip kernel support hc_head aiter#3044
- add scale_indexer_weights
…b + rotate_activation; 2. use topk_softplus fused kernel; 3. use mhc_pre in hc_head; 4. add scale_indexer_weights
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.