阿里云DSW环境，总是提示 The model's max seq len (8192) is larger than the maximum number of tokens that can be stored in KV cache (5392). Try increasing gpu_memory_utilization or decreasing max_model_len when initializing the engine.

[leeeex]

KwaiKEG/kagentlms_qwen_7b_mat
Qwen/Qwen-7B-Chat
两个都一样的提示。
尝试qwen1.5新版本，提示keyerror，qwen2

[leeeex]

python3 -m fastchat.serve.model_worker --model-path KwaiKEG/kagentlms_qwen_7b_mat --controller http://localhost:21001 --port 31000 --worker http://localhost:31000
查了fastchat官网，第二个服务用这个命令可以解决