Fix performance issue & bug on mps (Apple Silicon)#25
Open
sunnyden wants to merge 3 commits intoNVIDIA:mainfrom
Open
Fix performance issue & bug on mps (Apple Silicon)#25sunnyden wants to merge 3 commits intoNVIDIA:mainfrom
sunnyden wants to merge 3 commits intoNVIDIA:mainfrom
Conversation
sunnyden
changed the title
alex-audible
added a commit
to alex-audible/personaplex
that referenced
this pull request
Jan 28, 2026
- Apply PR NVIDIA#25 fixes for MPS compatibility: - lm.py: add map_location to torch.load for voice prompt embeddings - transformer.py: replace index_copy_ with direct assignment on MPS - Add MPS performance analysis (optimisation.md, optimisation_ultrathink.md) identifying 12 bottlenecks causing 5x slower-than-real-time inference - Add comprehensive MLX port plan (mlxport.md) with 6-stage approach, performance logging framework, and baseline-first methodology using existing test assets Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
On macOS the inference will have some bug and performance issue when running with args
--device mps.This PR fixed the issue.