Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi @antirez thanks for working on this implementation of voxtral, its very nice to have a dependency free way to run this model!
This PR adds support for int8 quantization which reduces the model memory usage and speeds up inference by +20% on my MBP M3 (roughly
37ms->28msper step)make testcomparisonbf16
quantized
jfk.wavcomparisonbf16
quantized
notes
voxtral_shaders.metalquantize_int8.ctool that quantizes the modelplease let me know if I should make any changes to this PR before it can be merged, or if these changes are not aligned with the project long term goals.
Thanks again!