Improve text-only decode performance#1105
Closed
lucasnewman wants to merge 1 commit into
Closed
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Only use MRoPE when we have a vision encoder and otherwise use the standard RoPE fast-path, which matches
mlx-lm. I tested a model from every model type that this touches for correctness, except forglm4v_moe, which was too large for my machine and was tested with synthetic weights.This improves decode performance for e.g.
mlx-community/Qwen3.5-0.8B-bf16from 203 tok/sec -> 233 tok/sec in the text-only case on my M5 Max for short generations.