Han Zhang
Han Zhang
For me, the reason that the docker closes as soon as I launched it is that the container cannot attach to my X11. To solve that: ```bash xhost +local:root ```
> > 我也有黑边 > > 转回wine了。。 wine体验如何？
别肝绘卷就行
Actually, I can reproduce all your results in the paper “statistical learning for accurate and interpretable battery lifetime prediction”, including the `variance` model. However, I cannot reproduce the `discharge` and...
Same error here. `pip freeze | grep torch` gives ``` pytorch-triton==2.1.0+9e3e10c5ed torch==2.1.0.dev20230723+cu121 torchaudio==2.1.0.dev20230723+cu121 torchelastic==0.2.2 torchtext==0.15.0 torchvision==0.16.0.dev20230723+cu121 ```
I also experienced this. To reproduce, add a single line into the `examples/offline_inference/torchrun_example.py`: ```python from vllm import LLM, SamplingParams prompts = [ "Hello, my name is", "The president of the...
OK. I think the issue it's on TRL side. My issue may be due to my local env. I do not experience any errors in my own RL architecture now.
I met this error again. Do you know what may be the cause? @youkaichao
> one possible workaround is to reimplement the sleep mode with dispatch mode Sounds like a lot of work. Can we skip the garbage collection for the tensors recorded in...