gpu_type: Iluvatar_bi-150
gpu_num: 1
command:
- vllm
- serve
- /model
- --served-model-name
- llm
- --max-model-len
- '4096'
- --gpu-memory-utilization
- '0.9'
- --enforce-eager
- --trust-remote-code
- -tp
- '1'
env:
- name: ENV_NAME
value: ENV_VALUE