52 lines
1.1 KiB
YAML
52 lines
1.1 KiB
YAML
services:
|
|
inference:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
image: rocm-vllm-inference:latest
|
|
container_name: rocm-vllm-inference
|
|
command: ["python", "-m", "app.start_api"]
|
|
ports:
|
|
- "8000:8000"
|
|
volumes:
|
|
- /opt/model:/opt/model:ro
|
|
- ./config.json:/workspace/config.json:ro
|
|
devices:
|
|
- /dev/kfd
|
|
- /dev/dri
|
|
group_add:
|
|
- video
|
|
- render
|
|
ipc: host
|
|
shm_size: 16g
|
|
cap_add:
|
|
- SYS_PTRACE
|
|
security_opt:
|
|
- seccomp=unconfined
|
|
restart: unless-stopped
|
|
openai_api:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
image: rocm-vllm-inference:latest
|
|
container_name: rocm-vllm-openai
|
|
command: ["python", "-m", "app.start_openai"]
|
|
ports:
|
|
- "8001:8001"
|
|
volumes:
|
|
- /opt/model:/opt/model:ro
|
|
- ./config.json:/workspace/config.json:ro
|
|
devices:
|
|
- /dev/kfd
|
|
- /dev/dri
|
|
group_add:
|
|
- video
|
|
- render
|
|
ipc: host
|
|
shm_size: 16g
|
|
cap_add:
|
|
- SYS_PTRACE
|
|
security_opt:
|
|
- seccomp=unconfined
|
|
restart: unless-stopped
|