26 lines
835 B
Plaintext
26 lines
835 B
Plaintext
# Example deployment for gpu-turnstile. Copy to compose.yaml and adjust.
|
|
#
|
|
# gpu-turnstile listens on the ports the services normally use; the actual
|
|
# Ollama and ComfyUI instances run one port higher on the workstation.
|
|
services:
|
|
gpu-turnstile:
|
|
image: git.rambossek.at/PUBLIC/gpu-turnstile:v0.1.1
|
|
restart: unless-stopped
|
|
environment:
|
|
OLLAMA_URL: http://<workstation-ip>:11435
|
|
COMFY_URL: http://<workstation-ip>:8189
|
|
# UNLOAD_TIMEOUT: 60s
|
|
# JOB_TIMEOUT: 15m
|
|
# LLM_WAIT_TIMEOUT: 10m
|
|
# WARM_MODEL: qwen3:14b
|
|
# LOG_LEVEL: info
|
|
# LOG_FORMAT: json
|
|
ports:
|
|
- "11434:11434" # LiteLLM api_base -> http://gpu-turnstile:11434
|
|
- "8188:8188" # Open WebUI COMFYUI_BASE_URL -> http://gpu-turnstile:8188
|
|
networks: [internal]
|
|
|
|
networks:
|
|
internal:
|
|
external: true
|