mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-10-14 23:58:11 +08:00
727c7b0dc6
support flash-attn in Dockerfile Former-commit-id: e30a47ab5bda9303c8a2eb814caf0dd40c01b125
33 lines
788 B
YAML
33 lines
788 B
YAML
services:
|
|
llamafactory:
|
|
build:
|
|
dockerfile: ./docker/docker-cuda/Dockerfile
|
|
context: ../..
|
|
args:
|
|
INSTALL_BNB: false
|
|
INSTALL_VLLM: false
|
|
INSTALL_DEEPSPEED: false
|
|
INSTALL_FLASH_ATTN: false
|
|
PIP_INDEX: https://pypi.org/simple
|
|
container_name: llamafactory
|
|
volumes:
|
|
- ../../hf_cache:/root/.cache/huggingface
|
|
- ../../ms_cache:/root/.cache/modelscope
|
|
- ../../data:/app/data
|
|
- ../../output:/app/output
|
|
ports:
|
|
- "7860:7860"
|
|
- "8000:8000"
|
|
ipc: host
|
|
tty: true
|
|
stdin_open: true
|
|
command: bash
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: "all"
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|