NVIDIA/TensorRT-LLM

TRT-LLM Discussion WeChat Group

Closed this issue · 5 comments

AdamzNV commented

欢迎扫描下图二维码，添加“小助手”微信，并在申请中备注“TRT-LLM”入群。

  1. 群内不定期更新最新Example，Benchmark，Training Video，Blog etcs。
  2. 在线实时QA，超过30位NV专家在线支持。

Image

mauriciosalvo commented

I am developing a project on my local machine and would like to know how I can access it with the command "docker pull nvcr.io/nvidia/tensorrt/tensorrt-llm:24.04-py3". Can anyone help me?

AdamzNV commented

I am developing a project on my local machine and would like to know how I can access it with the command "docker pull nvcr.io/nvidia/tensorrt/tensorrt-llm:24.04-py3". Can anyone help me?

https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tensorrt-llm/containers/release

ishw commented

添加好友显示“对方被添加为朋友过于频繁，请稍后再试”。。。可以放个入群二维码吗？

AdamzNV commented

添加好友显示“对方被添加为朋友过于频繁，请稍后再试”。。。可以放个入群二维码吗？

@ishw 可能太火爆了，你换个时间再试试吧。因为微信的原因，超过300人微信群不能用二维码扫描加入。

coolmanishks commented

Hi team i an working on gemma3 finetunned model on classification task with custom classification head , wanted to understand how i can convert to tensorRT format for faster inferencing , can anyone guide us what needs to be done