liweiqing1997
liweiqing1997
> Do you have unrelaxed pdb? And does it have many atom clashes? In alphafold code, **I thought** that was caused by newly created or discarded disulfide bonds during relaxation...
> Do you have `gcc` and `nvcc` on your PATH? You need both in order to run `setup.py` and train the model. On many systems, you can just run `module...
> It may be a permissions issue. [deepmind/alphafold#202](https://github.com/deepmind/alphafold/issues/202) That's true, thanks
This is a good job and I really need help with this job
vllm__version__ = "0.4.1"
> 这是一个相当旧的版本，您可以尝试使用较新版本的 vLLM 并看看问题是否仍然存在？ OK, We are currently testing. However, I would like to ask if it's possible to determine from the logs whether this error is caused by the...
Hello, I would like to inquire about the communication overhead of the current implementation. It seems that regardless of whether the MOE's EP (Expert Parallelism) is enabled, each rank will...
> [@liweiqing1997](https://github.com/liweiqing1997) Can you upload the model to HF for us to test? ModelScope is ok too. You can use this model: https://modelscope.cn/models/deepseek-ai/DeepSeek-V2-Lite-Chat/files. We also used this model, but only...
> [@liweiqing1997](https://github.com/liweiqing1997) Can you upload the quantized model so we can skip the slow quant stage and directly run it? I'm very sorry, our model involves private data and may...