Files
gpu-turnstile/compose.yaml.example
T
mram 20d5439b5f Retry upstream connection-refused with exponential backoff
A refused dial (service down/restarting) is retried with a wait that
doubles from BACKOFF_INITIAL (1s) up to BACKOFF_MAX (60s) until the
upstream answers or the client disconnects. Handles the Windows WSA
errno (10061) as well as POSIX ECONNREFUSED. compose.yaml.example now
uses host.docker.internal like the working local deployment.
2026-09-20 19:45:48 +02:00

32 lines
1.1 KiB
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 (11435 / 8189) and must
# bind 0.0.0.0 so the container can reach them (OLLAMA_HOST=0.0.0.0:11435,
# ComfyUI --listen 0.0.0.0 --port 8189).
services:
gpu-turnstile:
image: git.rambossek.at/public/gpu-turnstile:v0.1.1
restart: unless-stopped
environment:
# Services on the Docker host itself:
OLLAMA_URL: http://host.docker.internal:11435
COMFY_URL: http://host.docker.internal:8189
# Services on another machine: use its LAN IP instead, e.g.
# OLLAMA_URL: http://192.168.1.10:11435
# COMFY_URL: http://192.168.1.10:8189
# 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