38 lines
988 B
YAML
38 lines
988 B
YAML
services:
|
|
vllm:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
pull: false
|
|
image: vllm-openai-rocm:nightly
|
|
container_name: vllm-openai-rocm
|
|
entrypoint: ["python"]
|
|
command: ["-m", "app.start_openai"]
|
|
ports:
|
|
- "8001:8001"
|
|
volumes:
|
|
- /opt/model:/opt/model:ro
|
|
- ./config.json:/workspace/config.json:ro
|
|
environment:
|
|
HF_HOME: /opt/model
|
|
# 严格离线模式，禁止任何网络下载
|
|
HF_HUB_OFFLINE: "1"
|
|
TRANSFORMERS_OFFLINE: "1"
|
|
HF_DATASETS_OFFLINE: "1"
|
|
VLLM_ROCM_USE_AITER: "1" # 打开总开关
|
|
# 明确禁用不稳定的MoE后端，让其他AITER优化（如MHA）生效
|
|
VLLM_ROCM_USE_AITER_MOE: "0"
|
|
VLLM_ROCM_MOE_BACKEND: "TRITON" # 强制MoE使用Triton
|
|
devices:
|
|
- /dev/kfd
|
|
- /dev/dri
|
|
group_add:
|
|
- video
|
|
ipc: host
|
|
shm_size: 32g
|
|
cap_add:
|
|
- SYS_PTRACE
|
|
security_opt:
|
|
- seccomp=unconfined
|
|
restart: unless-stopped
|