Ethan Patterson

Results 4 issues of Ethan Patterson

用vllm项目的API部署,成功启动后,运行client_test.py后出现如下问题: ![image](https://github.com/FlagAlpha/Llama2-Chinese/assets/138442712/06be2ca8-5b8a-4121-922c-f46886de7c10) 请问各位大佬我该如何解决?

请问各位大佬,我在用该框架中的vllm加速baichuan2-13b时,按照步骤来创建了vllm的环境和依赖,运行后一直卡在这很久,但显存又在慢慢增加,是怎么回事呢? ![image](https://github.com/FlagAlpha/Llama2-Chinese/assets/138442712/2c3753b3-277b-4309-8507-5b182d2ebd59)

When I deployed internlm-20b-4bit using this framework, I commented out this part of the code and entered "Hello" in the generated browser, but there was no output or error. Therefore,...

环境:python=3.8,jittor=1.3.7.10,jtorch=0.1.7,在按照readme安装完后运行下列命令: export JT_SYNC=1 export trace_py_var=3 export JT_SAVE_MEM=1 export cpu_mem_limit=10000000000 export device_mem_limit=8000000000 conda activate jittorllm cd JittorLLMs/ python cli_demo.py chatglm 然后出现如下问题: [i 1015 22:19:39.834705 92 __init__.py:227] Total mem: 12.35GB, using 4...