Storm
Storm
When I conducted experiments using Baichuan 2-13B Chat, I found that the CPU utilization rate of each core was only 20%. I believe it is because BigDL LM did not...
### Describe the issue  hi, my machine is like this, I want to run benchmark, which command can get the best performance? The order I tried before was this,...
### Describe the issue May I ask if this library supports Qwen-14B Chat? If not supported, are there any adaptation plans in the future?
When i use python_api_example or streaming_llm python scripts to inference Qwen-14B-Chat，the first two questions were outputted normally, but the third question has been repeating itself since then. I find it...
### Is there an existing issue for this? - [X] I have searched the existing issues ### Environment ```markdown - Milvus version:v2.3.0-1977-g4ae7cabb0-dev - Deployment mode(standalone or cluster):standalone - MQ type(rocksmq,...
### Search before asking - [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar feature requirement. ### Description Have you considered adding user management and session management functions,...
### Search before asking - [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues. ### Operating system information Linux ### Python version information >=3.11 ### DB-GPT version...
机器A800，vLLM 0.5.0，prompt是开始，输出max tokens=2048，temperature设0.7 vLLM加载Qwen2-72B-Instruct-gptq-int4，使用vLLM的benchmark脚本来做并发测试，无论是1个并发限制还是10个并发限制，输出均会重复。 https://github.com/vllm-project/vllm/blob/main/benchmarks/benchmark_serving.py   当然我也测试了无限制并发的情况下，也会生成重复 
### Is there an existing issue for this bug? - [X] I have searched the existing issues ### 🐛 Describe the bug 当我启动训练的时候出现了下面的错误，怎么办？Ubuntu 22.04 ``` llama) root@autodl-container-ad594b8360-ad0d4c6e:~/autodl-tmp/ColossalAI/applications/ColossalChat/examples/training_scripts# bash train_sft.sh GPU...
支持qwen吗
