danvics/orpheus-fastapi
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update to compose file for my usage

Browse source
This commit is contained in:
The Guy 2025-07-16 09:35:15 -04:00
parent 3204232cd4
commit 67de795bdd
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
docker-compose-gpu.yml
View file

@ -9,13 +9,14 @@ services:
env_file: env_file:
- .env - .env
environment: environment:
# This internal communication uses Docker's network, not the host's localhost, so it's fine
- ORPHEUS_API_URL=http://llama-cpp-server:5006/v1/completions - ORPHEUS_API_URL=http://llama-cpp-server:5006/v1/completions
deploy: deploy:
resources: resources:
reservations: reservations:
devices: devices:
- driver: nvidia - driver: nvidia
count: all device_ids: ['0']
capabilities: [gpu] capabilities: [gpu]
restart: unless-stopped restart: unless-stopped
depends_on: depends_on:
@ -25,7 +26,8 @@ services:
llama-cpp-server: llama-cpp-server:
image: ghcr.io/ggml-org/llama.cpp:server-cuda image: ghcr.io/ggml-org/llama.cpp:server-cuda
ports: ports:
- "5006:5006" # Changed from "5006:5006" to bind only to localhost on the host
- "127.0.0.1:5006:5006"
volumes: volumes:
- ./models:/models - ./models:/models
env_file: env_file:
@ -38,7 +40,7 @@ services:
reservations: reservations:
devices: devices:
- driver: nvidia - driver: nvidia
count: all device_ids: ['0']
capabilities: [gpu] capabilities: [gpu]
restart: unless-stopped restart: unless-stopped
command: > command: >
@ -65,4 +67,3 @@ services:
echo "Model file already exists" echo "Model file already exists"
fi' fi'
restart: "no" restart: "no"