Skip to content

Add /api/unload endpoint to release GPU memory#103

Open
CameronSima wants to merge 1 commit intodevnen:mainfrom
CameronSima:claude/add-unload-endpoint-S3c46
Open

Add /api/unload endpoint to release GPU memory#103
CameronSima wants to merge 1 commit intodevnen:mainfrom
CameronSima:claude/add-unload-endpoint-S3c46

Conversation

@CameronSima
Copy link

Add endpoint to unload TTS model and release CUDA/GPU memory without restarting the server. Useful for freeing VRAM when TTS is not needed.

Add endpoint to unload TTS model and release CUDA/GPU memory without
restarting the server. Useful for freeing VRAM when TTS is not needed.
@crgmz
Copy link

crgmz commented Jan 9, 2026

@CameronSima shouldn't reload_model() be refactored to call the new unload_model()? It's just duplicated code at the moment

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants