Contact Information
19558772445
MaxKB Version
2.10.1(?)-2.10.3
Problem Description
使用vllm部署模型Qwen3-Reranker-8B curl正常 MaxKB调用报错 如下图
Steps to Reproduce
vllm部署Qwen3-Reranker-8B 模型从魔搭社区获取 使用参数
vllm serve /home/fit2cloud/models/Qwen3-Reranker-8B
--served-model-name Qwen3-Reranker-8B
--tensor-parallel-size 1
--gpu-memory-utilization 0.6
--host 0.0.0.0
--port 8002
--trust-remote-code
--max-model-len 32768
--runner pooling
--dtype auto
--enable-prefix-caching
The expected correct result
No response
Related log output
Additional Information
No response
Contact Information
19558772445
MaxKB Version
2.10.1(?)-2.10.3
Problem Description
使用vllm部署模型Qwen3-Reranker-8B curl正常 MaxKB调用报错 如下图
Steps to Reproduce
vllm部署Qwen3-Reranker-8B 模型从魔搭社区获取 使用参数
vllm serve /home/fit2cloud/models/Qwen3-Reranker-8B
--served-model-name Qwen3-Reranker-8B
--tensor-parallel-size 1
--gpu-memory-utilization 0.6
--host 0.0.0.0
--port 8002
--trust-remote-code
--max-model-len 32768
--runner pooling
--dtype auto
--enable-prefix-caching
The expected correct result
No response
Related log output
Additional Information
No response