framework: vllm
api: completion
lang: en
max_model_len: 4096
max_tokens: 1024
temperature: 0.7
repetition_penalty: 1.1
top_p: 0.9
sut_config:
  gpu_num: 1
  values:
    command:
    - /opt/conda/bin/vllm
    - serve
    - /model
    - --port
    - '20644'
    - --served-model-name
    - llm
    - --max-model-len
    - '4096'
    - --gpu-memory-utilization
    - '0.9'
    - -tp
    - '1'
    - --enforce-eager
    - --trust-remote-code
ref_config:
  gpu_num: 1
  values:
    command:
    - vllm
    - serve
    - /model
    - --port
    - '80'
    - --served-model-name
    - llm
    - --max-model-len
    - '4096'
    - -tp
    - '1'
    - --enforce-eager
    - --trust-remote-code