ViperEkura
5756054d38
- Add cu128/cu130 build matrix to release workflow - Parametrize Dockerfile and docker-compose with CUDA_TAG build arg - Allow csrc/ and setup.py in docker context via .dockerignore - Add nvcc/torch CUDA version mismatch preflight warning in setup.py - Add cuda_toolkit_version() helper in csrc/build.py - Use at::IntArrayRef explicitly to fix ATen overload ambiguity - Guard kernels with CUDART_VERSION >= 11020 check - Remove invalid [tool.pip] section from pyproject.toml
49 lines
1.1 KiB
YAML
49 lines
1.1 KiB
YAML
services:
|
|
server:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
CUDA_TAG: ${CUDA_TAG:-cu128}
|
|
user: "${UID:-1000}:${GID:-1000}"
|
|
ports:
|
|
- "8000:8000"
|
|
volumes:
|
|
- ./params:/app/params:ro
|
|
command: python -m scripts.tools.server --port 8000 --device cuda
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 60s
|
|
restart: unless-stopped
|
|
|
|
server-cpu:
|
|
profiles: [cpu]
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
CUDA_TAG: ${CUDA_TAG:-cu128}
|
|
user: "${UID:-1000}:${GID:-1000}"
|
|
ports:
|
|
- "8000:8000"
|
|
volumes:
|
|
- ./params:/app/params:ro
|
|
command: python -m scripts.tools.server --port 8000 --device cpu
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
restart: unless-stopped
|