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.

This commit is contained in:

mram

2026-09-20 18:05:20 +02:00

commit 065c294a96

14 changed files with 2027 additions and 0 deletions

									
										go.mod
									
		+3
		
												View File
												
				@@ -0,0 +1,3 @@

				module gpu-turnstile

				go 1.23