发布

  • model: fix qwen3 tool calling in thinking (#14477)

    frostbyte_neo 发布于 2026-02-27 00:13:18 +00:00

    Align Qwen parser behavior with Transformers serve by allowing <tool_call> parsing while still in thinking collection.

    Changes:

    • qwen3vl: detect <tool_call> before in thinking state and transition to tool parsing

    • qwen3: same thinking-state tool detection and partial-tag overlap handling

    • tests: update qwen3vl thinking/tool interleaving expectations

    • tests: add qwen3 cases for tool call before and split <tool_call> streaming

    下载附件