Files

24 lines
631 B
YAML

# include:
# - compose.observability.yaml
services:
speaches:
extends:
file: compose.yaml
service: speaches
# NOTE: slightly older cuda version is available under 'latest-cuda-12.4.1' and `latest-cuda-12.6.3` tags
image: ghcr.io/speaches-ai/speaches:latest-cuda
build:
args:
BASE_IMAGE: nvidia/cuda:12.9.0-cudnn-runtime-ubuntu24.04
volumes:
- hf-hub-cache:/home/ubuntu/.cache/huggingface/hub
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
hf-hub-cache: