Skip to content

temperature is not supported for Qwen3-ASR #4996

@x303597316

Description

@x303597316

System Info / 系統信息

2.9.0版本,部署qwen3-asr,调用时报
2026-06-06 03:29:18,001 xinference.core.model 6278 DEBUG [request e65bc3b2-6157-11f1-bf8a-0242ac110002] Enter transcriptions, args: ModelActor(Qwen3-ASR-1.7B-0), kwargs: language=zh,prompt=None,response_format=json,temperature=0.7,timestamp_granularities=None
2026-06-06 03:29:18,002 xinference.core.model 6278 ERROR [request e65bc3b2-6157-11f1-bf8a-0242ac110002] Leave transcriptions, error: temperature is not supported for Qwen3-ASR, elapsed time: 0 s
Traceback (most recent call last):
File "/opt/inference/xinference/core/utils.py", line 95, in wrapped
ret = await func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/inference/xinference/core/model.py", line 802, in transcriptions
return await self._call_wrapper_json(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/inference/xinference/core/model.py", line 569, in _call_wrapper_json
return await self._call_wrapper("json", fn, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/inference/xinference/core/model.py", line 140, in _async_wrapper
return await fn(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/inference/xinference/core/model.py", line 594, in _call_wrapper
ret = await asyncio.to_thread(fn, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/threads.py", line 25, in to_thread
return await loop.run_in_executor(None, func_call)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/concurrent/futures/thread.py", line 59, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/inference/xinference/model/audio/qwen3_asr.py", line 116, in transcriptions
raise RuntimeError("temperature is not supported for Qwen3-ASR")
RuntimeError: temperature is not supported for Qwen3-ASR
2026-06-06 03:29:18,004 xinference.core.model 6278 DEBUG After request transcriptions, current serve request count: -1 for the model Qwen3-ASR-1.7B-0

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?

  • docker / docker
  • pip install / 通过 pip install 安装
  • installation from source / 从源码安装

Version info / 版本信息

2.9.0

The command used to start Xinference / 用以启动 xinference 的命令

docker run

Reproduction / 复现过程

大模型语音识别时报错

Expected behavior / 期待表现

能成功调用asr

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions