PUBLIC/gpu-turnstile
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 9 Wiki Activity
43 Commits 1 Branch 15 Tags
e43ad02fc4620c03c89428af382e5579cb9b8a4e
Commit Graph
5 Commits
Author SHA1 Message Date
mram e43ad02fc4 Ignore staged-update leftovers next to the dev exe 2026-09-21 13:14:33 +02:00
mram d1e01f9b78 Ignore signing/ directory (Ed25519 release keys) 2026-09-20 22:13:10 +02:00
mram cef845c2e3 Add compose.yaml.example; ignore local compose files 2026-09-20 19:24:26 +02:00
mram db11da8307 Rename to gpu-turnstile; swap port roles 
The proxy now listens on the standard service ports (Ollama :11434,
ComfyUI :8188) and the actual services move one port up (:11435, :8189).
Metric prefix is now gpu_turnstile_.
 2026-09-20 18:10:22 +02:00
mram 065c294a96 gpulock: GPU arbitration proxy for Ollama + ComfyUI 
Implements SPEC.md: two listeners, one writer-preferring two-mode lock,
Ollama unload before image jobs, ComfyUI history polling + VRAM free,
optional model warm-up, healthz/metrics endpoints, streaming-safe
reverse proxies, Dockerfile and Gitea Actions CI.
 2026-09-20 18:05:20 +02:00