Tool call parser configuration¶
In the context of deploying Large Language Models (LLMs) for Agentic workflows, tool call parser configuration refers to the specific parameter settings that enable a model to correctly interpret and execute function calls^[001-TODO__Qwen_3.6_27B_—面向_Coding_Agent_的开源模型.md]. While some models may only describe tool usage, an Agentic model requires specific configurations to actually invoke tools^[001-TODO__Qwen_3.6_27B—_面向_Coding_Agent_的开源模型.md].
For the Qwen 3.6 27B model deployed via vLLM, this configuration is critical for shifting the model from a descriptive mode to an executable mode^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md].
Key Configuration Parameters¶
When launching a vLLM instance, two specific parameters are primarily responsible for enabling tool use capabilities^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md]:
--enable-auto-tool-choice: This flag must be enabled to ensure the model actively chooses and executes tools. If omitted, the model may act as a "chatterbox," describing how a tool should be used without ever triggering the actual function call^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md].--tool-call-parser: This argument tells the inference engine how to interpret the model's output specifically for tool calls. For Qwen 3.x models, the value must be set toqwen3to ensure format compatibility^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md].
Implementation Example¶
A complete vLLM startup command configuring these parsers for Qwen 3.6 27B would look like this^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md]:
vllm serve Qwen/Qwen3-27B \
--port 8000 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--enable-auto-tool-choice \
--tool-call-parser qwen3
Troubleshooting¶
- Incorrect Parser: Failing to set the parser to
qwen3can lead to tool call format mismatches, causing the agent to fail execution^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md]. - Missing Auto-Choice: Without
--enable-auto-tool-choice, the agent may revert to explaining its actions rather than performing them^[001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md].
Related Concepts¶
- [[Qwen 3.6 27B]]
- [[vLLM]]
- Hermes Agent
Sources¶
001-TODO__Qwen_3.6_27B_—_面向_Coding_Agent_的开源模型.md