TAO JIANG
TAO JIANG
你解决了吗？我也报这个错
> 我知道为什么... 在 中`actor.py`，检查点被保存为键“model”的值，而在保存 LLaMA 模型时则不需要。  > > 所以在 中`llama_model.py`，`def load_checkpoints`应该这样修改：  Thank you, after reading your answer, I successfully got the code to run on multiple GPUs, but...
> She seems to be Japanese, does Japan also use QQ?😊
> You have good eyesight!!
> > > > > > > > > You have good eyesight!! > > Did you run it successfully? I think we can provide a QQ group chat account...
> > > > > > > > > > > > > > > > > You have good eyesight!! > > > > > > > > >...
> Known problem sadly :( I just didn't know how to fix it - I'm assuming ur calling `get_chat_template` more than once in the notebook correct? No, I just got...
I also want to know if it can support onnx model
> @Xu-Chen @lxww302 I noticed that you have used the implementation of SGLang's DeepSeek V2 TP8 MLA before. Could you help verify the performance of the new version, for example,...
> python3 -m sglang.check_env ``` Python: 3.12.3 | packaged by Anaconda, Inc. | (main, May 6 2024, 19:46:43) [GCC 11.2.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: NVIDIA H100 80GB HBM3 GPU...