TypeError: StopIteration interacts badly with generators and cannot be raised into a Future #4165
Description
System Info / 系統信息
CUDA Version: 13.0
Driver Version: 580.95.05
操作系统：Ubuntu
模型：DeepSeek-R1-Distill-Llama-70B-GGUF
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
v1.9.0
The command used to start Xinference / 用以启动 xinference 的命令
docker run -d
--name xinference-server
-v /data/xinference/.xinference:/root/.xinference
-v /data/xinference/.cache/huggingface:/root/.cache/huggingface
-v /data/xinference/.cache/modelscope:/root/.cache/modelscope
-p 9997:9997
--gpus all
xprobe/xinference:v1.7.0
xinference-local -H 0.0.0.0
Reproduction / 复现过程
1、使用本地已下载好的量化后的模型：
DeepSeek-R1-Distill-Llama-70B-Q6_K-00001-of-00002.gguf
DeepSeek-R1-Distill-Llama-70B-Q6_K-00002-of-00002.gguf
2、运行参数配置（Web UI）
Model Path：/root/.xinference/models/deepseek-70B-Q8/DeepSeek-R1-Distill-Llama-70B-Q8_0-00001-of-00002.gguf
Model Engine：vLLM
Model Format：ggufv2
Model Size：70
Quantization：Q8_0
GPU Count per worker：2
N GPU Layers：-1
Replica：1
gpu_memory_utilization：0.8
max_model_len：8000
3、运行模型报错，日志如下：
INFO 10-22 18:07:38 [init.py:239] Automatically detected platform cuda.
2025-10-22 18:07:41,960 xinference.core.model 496 INFO Start requests handler.
/opt/inference/xinference/model/llm/core.py:143: UserWarning: enable_thinking cannot be disabled for non hybrid model, will be ignored
warnings.warn(
ERROR:asyncio:Exception in callback _chain_future.._set_state(<Future pendi...ask_wakeup()]>, <Future at 0x...StopIteration>) at /usr/lib/python3.10/asyncio/futures.py:379
handle: <Handle _chain_future.._set_state(<Future pendi...ask_wakeup()]>, <Future at 0x...StopIteration>) at /usr/lib/python3.10/asyncio/futures.py:379>
Traceback (most recent call last):
File "/usr/lib/python3.10/asyncio/events.py", line 80, in _run
self._context.run(self._callback, *self._args)
File "/usr/lib/python3.10/asyncio/futures.py", line 381, in _set_state
_copy_future_state(other, future)
File "/usr/lib/python3.10/asyncio/futures.py", line 357, in _copy_future_state
dest.set_exception(_convert_future_exc(exception))
TypeError: StopIteration interacts badly with generators and cannot be raised into a Future
Expected behavior / 期待表现
使用vLLM运行成功