mirror of
https://github.com/fauxpilot/fauxpilot.git
synced 2025-03-12 04:36:10 -07:00
283668448d
* Create publish-docker-images.yaml * Add copilot_proxy publishing * Add model_converter publishing * Use dockerhub version * Do not login for PRs * Overwrite some of labels value * Move ignore files to the root of `context` * Add comments & fix some issue * Fix typos * Remove the target of the master branch * Delete .dockerignore * Delete .dockerignore * Add Flake8 * Add Flake8 and format code accordingly * Iterate on the PR template, fix the token for the contributor action * Remove converter image build * Update Dockerfile of proxy * Comment out proxy image in compose Co-authored-by: Fred de Gier <freddegier@me.com> * Fix build action --------- Co-authored-by: Rowe Wilson Frederisk Holme <frederisk@outlook.com>
36 lines
938 B
YAML
36 lines
938 B
YAML
version: '3.3'
|
|
services:
|
|
triton:
|
|
build:
|
|
context: .
|
|
dockerfile: triton.Dockerfile
|
|
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
|
|
- ${HF_CACHE_DIR}:/root/.cache/huggingface
|
|
ports:
|
|
- "8000:8000"
|
|
- "${TRITON_PORT}:8001"
|
|
- "8002:8002"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
copilot_proxy:
|
|
# For dockerhub version
|
|
# image: moyix/copilot_proxy:latest
|
|
# For local build
|
|
build:
|
|
context: .
|
|
dockerfile: proxy.Dockerfile
|
|
command: uvicorn app:app --host 0.0.0.0 --port 5000
|
|
env_file:
|
|
# Automatically created via ./setup.sh
|
|
- .env
|
|
ports:
|
|
- "${API_EXTERNAL_PORT}:5000"
|