jamiepineandcapy-ai-staging[bot] dd8ab5cb20 fix(mlx): fold Qwen3 LLM load+generate into one worker submission; bind model locally in generate closures ...

Review follow-ups on the thread-affinity PR: MLXQwenLLMBackend.generate
awaited load_model as one worker submission and then submitted
_generate_sync as a second, leaving the same load/generate gap the TTS
and STT paths close (a concurrent load_model for another size or an
unload could swap or null out self.model/self.tokenizer in between).
Give the LLM backend the same _op_lock + single _reload_and_generate_sync
shape. The TTS/STT/LLM sync closures now bind the model to a local once,
so an inline unload_model() from the event loop mid-generation cannot
turn a later self.model read (the voice-clone fallback path in
particular) into an AttributeError.

2026-10-04 00:01:47 +00:00

..

__init__.py

fix(kokoro): trim edges only, keep inter-segment gaps

2026-10-04 00:01:24 +00:00

base.py

refactor(generation): simplify post-generation cache cleanup

2026-10-04 00:01:18 +00:00

chatterbox_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

chatterbox_turbo_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

hume_backend.py

fix(tada): run voice-prompt encode under torch.inference_mode (#955)

2026-07-26 23:31:20 -07:00

kokoro_backend.py

fix(kokoro): trim edges only, keep inter-segment gaps

2026-10-04 00:01:24 +00:00

luxtts_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

mlx_backend.py

fix(mlx): fold Qwen3 LLM load+generate into one worker submission; bind model locally in generate closures

2026-10-04 00:01:47 +00:00

pytorch_backend.py

refactor(stt): name the Whisper sample rate and window constants

2026-10-04 00:01:34 +00:00

qwen_custom_voice_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

qwen_llm_backend.py

fix(mlx): fold Qwen3 LLM load+generate into one worker submission; bind model locally in generate closures

2026-10-04 00:01:47 +00:00