Fix audio server defaults and CUDA fallback#46
Open
Th0rgal wants to merge 5 commits intoFunAudioLLM:mainfrom
Open
Fix audio server defaults and CUDA fallback#46Th0rgal wants to merge 5 commits intoFunAudioLLM:mainfrom
Th0rgal wants to merge 5 commits intoFunAudioLLM:mainfrom
Conversation
Th0rgal
commented
Feb 10, 2026
Th0rgal
commented
- Align simple_server.py with web_demo defaults for speech generation\n- Add bad_words_ids in generation kwargs\n- Add CUDA arch hint and nvfuser disable helper\n\nNote: CUDA kernel compilation still fails on GB10 unless CUDA is disabled; I ran server with CUDA_VISIBLE_DEVICES="" to validate end-to-end audio.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.