feat: Apple Silicon MPS support (bf16, no autocast) - #56
Open
yhsung wants to merge 1 commit into
Open
Conversation
- resolve_device auto now prefers cuda, then mps, then cpu - pass device through to audio processor on mps - keep autocast cuda-only: autocast on mps produces degenerate all-zero output, bf16 weights run correctly without it Measured on M-series Mac: 10-min audio in ~4:20 (RTF ~0.44), ~2.4x faster than CPU, identical segments.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Measured on M-series Mac: 10-min audio in ~4:20 (RTF ~0.44), ~2.4x faster than CPU, identical segments.
Closes fork ahead by 1 commit (dc42ba3).