tlg aa7a160118 fix: proper VRAM cleanup on model unload + CUDA alloc config ...

- Force gc.collect() before torch.cuda.empty_cache() to ensure all
  model references are released
- Set PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True in container

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-05 17:59:23 +02:00

..

config

feat: project scaffolding with config files and test fixtures

2026-04-04 07:23:14 +02:00

docs/superpowers

Add llmux implementation plan (30 tasks)

2026-04-03 22:43:37 +02:00

llmux

fix: proper VRAM cleanup on model unload + CUDA alloc config

2026-04-05 17:59:23 +02:00

scripts

fix: use LLMUX_SRC env var for Dockerfile path in pod creation script

2026-04-05 13:05:38 +02:00

tests

feat: API routes for models, chat, transcription, speech, and admin

2026-04-05 10:04:45 +02:00

Dockerfile

fix: proper VRAM cleanup on model unload + CUDA alloc config

2026-04-05 17:59:23 +02:00

requirements.txt

fix: Dockerfile uses explicit pip install, skip pre-installed packages

2026-04-05 14:10:07 +02:00