Duplicated from  KyleHessling1/Qwopus3.5-27B-v3-FP8-vllm-ready

Jackrong

/

Qwopus3.5-27B-v3-FP8-vllm-ready

like 14

Same error 😂

vllm version is:

vllm --version
0.19.0

transformers is

uv pip list | grep transformers
Using Python 3.12.3 environment at: vllm/.venv
transformers                             5.5.0

serve command is:

vllm serve ./models/qwen/qwopus3.5-27b-v3-fp8-vllm-ready   \
  --dtype bfloat16  \
  --gpu-memory-utilization 0.93   \
  --max-model-len 2048   \
  --enforce-eager  \
   --trust-remote-code \
  --served-model-name qwopus3.5-27b-v3

Error message is:

(APIServer pid=3732473)   File "~/Developer/llm/vllm/.venv/lib/python3.12/site-packages/vllm/model_executor/models/qwen3_5.py", line 110, in get_hf_config
(APIServer pid=3732473)     return self.ctx.get_hf_config(Qwen3_5Config)
(APIServer pid=3732473)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=3732473)   File "~/Developer/llm/vllm/.venv/lib/python3.12/site-packages/vllm/multimodal/processing/context.py", line 140, in get_hf_config
(APIServer pid=3732473)     raise TypeError(
(APIServer pid=3732473) TypeError: Invalid type of HuggingFace config. Expected type: <class 'vllm.transformers_utils.configs.qwen3_5.Qwen3_5Config'>, but found type: <class 'transformers.models.qwen3_5.configuration_qwen3_5.Qwen3_5TextConfig'>

Hi, thanks for all! Just want to say that I got the same bug! Any docker image should I use?

Same here

same here

Same, seems like this is borked.