Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-19 14:50:38 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(mlx): serialize accelerator lifecycle and inference

Browse Source 
Route MLX load, inference, unload, reset, cache cleanup, and shutdown through a single worker. Add affinity and concurrent-unload regression coverage.\n\nVerified: 17 related backend tests; frontend CI; cargo check.
This commit is contained in:
Jamie Pine
2026-07-19 17:40:03 -07:00
parent f2cf2a729d
commit 5fd95b3dcc
10 changed files with 286 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app.py
+3 -3
View File
@@ -353,15 +353,15 @@ async def _run_shutdown() -> None:
"""Unload models on lifespan exit."""
logger.info("Voicebox server shutting down...")
try:
tts.unload_tts_model()
await tts.unload_tts_model()
except Exception:
logger.exception("Failed to unload TTS model")
try:
transcribe.unload_whisper_model()
await transcribe.unload_whisper_model()
except Exception:
logger.exception("Failed to unload Whisper model")
try:
llm.unload_llm_model()
await llm.unload_llm_model()
except Exception:
logger.exception("Failed to unload LLM model")