tlg d7a091df8c feat: VRAM manager with priority-based model eviction ...

Tracks GPU VRAM usage (16GB) and handles model loading/unloading with
priority-based eviction: LLM (lowest) -> TTS -> ASR (highest, protected).
Uses asyncio Lock for concurrency safety.

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

2026-04-04 09:14:41 +02:00

kischdle/llmux

feat: VRAM manager with priority-based model eviction

2026-04-04 09:14:41 +02:00

.gitignore

Initial commit with .gitignore

2026-03-31 17:58:54 +02:00

Description

No description provided

144 KiB

Languages

Python 91.2%

Shell 6%

Dockerfile 2.8%