-
Stefy Lanza (nextime / spora ) authoredWhen vllm.enabled, the front-proxy spawns a dedicated 'vllm' engine on the NVIDIA card(s) with capability {vllm} only (mirrors the nvidia-gguf split) — a real subprocess, so it appears in the engine/task page and routing/VRAM/thermal apply. Models pinned backend:vllm route to it; vllm removed from the shared _DEFAULT_CAPS so no other node claims them. vllm.gpu -> that node's CUDA_VISIBLE_DEVICES/CODERAI_ENGINE_GPUS. CUDA-only. Co-Authored-By:Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Mw2KQiswmD69T45fTfjKwW
b9a84c01
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| __init__.py | ||
| admin_data.py | ||
| app.py | ||
| assignment.py | ||
| engine_supervisor.py | ||
| gpu_detect.py | ||
| registry.py | ||
| reqqueue.py | ||
| router.py | ||
| ui_pages.py |