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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Renamed Docker and compose files to clearly target AMD Strix Halo hardware and updated references accordingly.
Added bfloat16 optimization for the T3 model with autocast support, improving token generation speed by ~40% while keeping S3Gen in float32 for stability.
Introduced a voice conditioning cache to skip redundant voice encoding, saving 2–5 seconds on repeat requests.
Added configurable TTS_BF16 env var with auto hardware detection and backward-compatible fallbacks across GPUs/CPU.
Patched torch 2.9+ dtype issues and tuned Strix Halo ROCm settings, delivering 50% faster inference with zero breaking changes.
Before:
After:
