mirror of
https://github.com/fauxpilot/fauxpilot.git
synced 2025-03-12 04:36:10 -07:00
33 lines
868 B
YAML
33 lines
868 B
YAML
version: '3.3'
|
|
services:
|
|
triton:
|
|
image: moyix/triton_with_ft:22.09
|
|
command: bash -c "CUDA_VISIBLE_DEVICES=${GPUS} mpirun -n 1 --allow-run-as-root /opt/tritonserver/bin/tritonserver --model-repository=/model"
|
|
shm_size: '2gb'
|
|
volumes:
|
|
- ${MODEL_DIR}:/model
|
|
ports:
|
|
- "8000:8000"
|
|
- "8001:8001"
|
|
- "8002:8002"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
copilot_proxy:
|
|
# For dockerhub version
|
|
# image: moyix/copilot_proxy:latest
|
|
# command: python3 -m flask run --host=0.0.0.0 --port=5000
|
|
# For local build
|
|
build:
|
|
context: .
|
|
dockerfile: copilot_proxy/Dockerfile
|
|
env_file:
|
|
# Automatically created via ./setup.sh
|
|
- .env
|
|
ports:
|
|
- "${API_EXTERNAL_PORT}:5000"
|