root
33 lines
861 B
YAML
33 lines
861 B
YAML
name: gpu-lab-vllm-modern
|
|
services:
|
|
vllm-modern:
|
|
image: vllm/vllm-openai:v0.8.5.post1
|
|
container_name: gpu-lab-vllm-modern
|
|
network_mode: host
|
|
ipc: host
|
|
shm_size: "32gb"
|
|
volumes:
|
|
- /root/models:/models:ro
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
entrypoint: ["/bin/sh", "-c"]
|
|
command:
|
|
- >
|
|
exec python3 -m vllm.entrypoints.openai.api_server
|
|
--model /models/deepseek-coder-v2-lite
|
|
--served-model-name deepseek-coder-v2-lite
|
|
--host 0.0.0.0 --port 8010
|
|
--tensor-parallel-size 2
|
|
--dtype bfloat16
|
|
--max-model-len 8192
|
|
--gpu-memory-utilization 0.9
|
|
--max-num-seqs 4
|
|
--trust-remote-code
|
|
--enforce-eager
|
|
restart: "no"
|