qwen 系列模型涉及到的部署、推理

来源 https://qwen.readthedocs.io/en/latest/quantization/awq.html

• 其中关于智能体部分

importos from qwen_agent.agentsimportAssistant# Define LLMllm_cfg={# Use a custom endpoint compatible with OpenAI API by vLLM/SGLang:'model':'Qwen/Qwen3-32B','model_server':'http://localhost:8000/v1',# api_base'api_key':'EMPTY',# 'generate_cfg': {# # When using vLLM/SGLang OAI API, pass the parameter of whether to enable thinking mode in this way# 'extra_body': {# 'chat_template_kwargs': {'enable_thinking': False}# },## # Add: When the content is `<think>this is the thought</think>this is the answer`# # Do not add: When the response has been separated by reasoning_content and content# # This parameter will affect the parsing strategy of tool call# # 'thought_in_content': True,# },}# llm_cfg = {# # Use the model service provided by DashScope:# 'model': 'qwen3-235b-a22b',# 'model_type': 'qwen_dashscope',## # 'generate_cfg': {# # # When using the Dash Scope API, pass the parameter of whether to enable thinking mode in this way# # 'enable_thinking': False,# # },# }# llm_cfg = {# # Use the OpenAI-compatible model service provided by DashScope:# 'model': 'qwen3-235b-a22b',# 'model_server': 'https://dashscope.aliyuncs.com/compatible-mode/v1',# 'api_key': os.getenv('DASHSCOPE_API_KEY'),## # 'generate_cfg': {# # # When using Dash Scope OAI API, pass the parameter of whether to enable thinking mode in this way# # 'extra_body': {# # 'enable_thinking': False# # },# # },# }# Define Toolstools=[{'mcpServers':{# You can specify the MCP configuration file'time':{'command':'uvx','args':['mcp-server-time','--local-timezone=Asia/Shanghai']},"fetch":{"command":"uvx","args":["mcp-server-fetch"]}}},'code_interpreter',# Built-in tools]# Define Agentbot=Assistant(llm=llm_cfg,function_list=tools)# Streaming generationmessages=[{'role':'user','content':'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]forresponsesinbot.run(messages=messages): pass print(responses)