使用示例#

使用本地模型推理#

本项目支持本地transformers进行推理和vllm推理（需先安装vllm）， --model可以填入modelscope模型名称，例如Qwen/Qwen2.5-0.5B-Instruct；也可以直接指定模型权重路径，例如/path/to/model_weights，无需指定--url参数。

1. 使用transformers进行推理

指定--api local：

evalscope perf \
 --model 'Qwen/Qwen2.5-0.5B-Instruct' \
 --attn-implementation flash_attention_2 \  # 可不填，或选[flash_attention_2|eager|sdpa]
 --number 20 \
 --rate 2 \
 --api local \
 --dataset openqa

2. 使用vllm进行推理

指定--api local_vllm：

evalscope perf \
 --model 'Qwen/Qwen2.5-0.5B-Instruct' \
 --number 20 \
 --rate 2 \
 --api local_vllm \
 --dataset openqa

使用prompt#

evalscope perf \
 --url 'http://127.0.0.1:8000/v1/chat/completions' \
 --rate 2 \
 --model 'qwen2.5' \
 --log-every-n-query 10 \
 --number 20 \
 --api openai \
 --temperature 0.9 \
 --max-tokens 1024 \
 --prompt '写一个科幻小说，请开始你的表演'

也可以使用本地文件作为prompt：

evalscope perf \
 --url 'http://127.0.0.1:8000/v1/chat/completions' \
 --rate 2 \
 --model 'qwen2.5' \
 --log-every-n-query 10 \
 --number 20 \
 --api openai \
 --temperature 0.9 \
 --max-tokens 1024 \
 --prompt @prompt.txt

复杂请求#

使用stop，stream，temperature等：

evalscope perf \
 --url 'http://127.0.0.1:8000/v1/chat/completions' \
 --rate 2 \
 --model 'qwen2.5' \
 --log-every-n-query 10 \
 --read-timeout 120 \
 --connect-timeout 120 \
 --number 20 \
 --max-prompt-length 128000 \
 --min-prompt-length 128 \
 --api openai \
 --temperature 0.7 \
 --max-tokens 1024 \
 --stop '<|im_end|>' \
 --dataset openqa \
 --stream

使用query-template#

您可以在query-template中设置请求参数：

evalscope perf \
 --url 'http://127.0.0.1:8000/v1/chat/completions' \
 --rate 2 \
 --model 'qwen2.5' \
 --log-every-n-query 10 \
 --read-timeout 120 \
 --connect-timeout 120 \
 --number 20 \
 --max-prompt-length 128000 \
 --min-prompt-length 128 \
 --api openai \
 --query-template '{"model": "%m", "messages": [{"role": "user","content": "%p"}], "stream": true, "skip_special_tokens": false, "stop": ["<|im_end|>"], "temperature": 0.7, "max_tokens": 1024}' \
 --dataset openqa

其中%m和%p会被替换为模型名称和prompt。

您也可以使用本地query-template.json文件：

template.json#
{
   "model":"%m",
   "messages":[
      {
         "role":"user",
         "content":"%p"
      }
   ],
   "stream":true,
   "skip_special_tokens":false,
   "stop":[
      "<|im_end|>"
   ],
   "temperature":0.7,
   "max_tokens":1024
}

evalscope perf \
 --url 'http://127.0.0.1:8000/v1/chat/completions' \
 --rate 2 \
 --model 'qwen2.5' \
 --log-every-n-query 10 \
 --read-timeout 120 \
 --connect-timeout 120 \
 --number 20 \
 --max-prompt-length 128000 \
 --min-prompt-length 128 \
 --api openai \
 --query-template @template.json \
 --dataset openqa

使用wandb记录测试结果#

请安装wandb：

pip install wandb

在启动时，添加以下参数，即可：

--wandb-api-key 'wandb_api_key'
--name 'name_of_wandb_log'

wandb sample

调试请求#

使用 --debug 选项，我们将输出请求和响应，输出示例如下：

非stream模式输出示例

2024-11-27 11:25:34,161 - evalscope - http_client.py - on_request_start - 116 - DEBUG - Starting request: <TraceRequestStartParams(method='POST', url=URL('http://127.0.0.1:8000/v1/completions'), headers=<CIMultiDict('Content-Type': 'application/json', 'user-agent': 'modelscope_bench', 'Authorization': 'Bearer EMPTY')>)>
2024-11-27 11:25:34,163 - evalscope - http_client.py - on_request_chunk_sent - 128 - DEBUG - Request sent: <method='POST',  url=URL('http://127.0.0.1:8000/v1/completions'), truncated_chunk='{"prompt": "hello", "model": "qwen2.5"}'>
2024-11-27 11:25:38,172 - evalscope - http_client.py - on_response_chunk_received - 140 - DEBUG - Request received: <method='POST',  url=URL('http://127.0.0.1:8000/v1/completions'), truncated_chunk='{"id":"cmpl-a4565eb4fc6b4a5697f38c0adaf9b70b","object":"text_completion","created":1732677934,"model":"qwen2.5","choices":[{"index":0,"text":"，everyone！今天我给您撒个谎哦。 ))\\n\\n今天开心的事。","logprobs":null,"finish_reason":"length","stop_reason":null,"prompt_logprobs":null}],"usage":{"prompt_tokens":1,"total_tokens":17,"completion_tokens":16}}'>

stream模式输出示例

2024-11-27 20:02:24,760 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"重要的"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:24,803 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":""},"finish_reason":null}],"usage":null}
2024-11-27 20:02:24,847 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"，以便"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:24,890 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"及时"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:24,933 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"得到"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:24,976 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"帮助"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:25,023 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"和支持"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:25,066 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":""},"finish_reason":null}],"usage":null}
2024-11-27 20:02:25,109 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":""},"finish_reason":null}],"usage":null}
2024-11-27 20:02:25,111 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"。<|im_end|>"},"finish_reason":null}],"usage":null}
2024-11-27 20:02:25,113 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: {"model":"Qwen2.5-0.5B-Instruct","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":50,"completion_tokens":260,"total_tokens":310}}
2024-11-27 20:02:25,113 - evalscope - http_client.py - _handle_stream - 57 - DEBUG - Response recevied: data: [DONE]