Ethan (Yusheng) Su
Ethan (Yusheng) Su
Hello, @106753004 @autoliuweijie I also want to implement K-BERT on the English corpus. @autoliuweijie the model you mentioned is Google pre-trained Bert on Wiki right, or have you already done...
@BillGundas . I think you can follow the [getting started](https://github.com/OpenBMB/AgentVerse#-getting-started) to run it. Did you encounter any problems?
@shanggangli Currently, we only support OpenAI's models. If you want to use your local models, you need to create a python script at here: https://github.com/OpenBMB/AgentVerse/tree/main/agentverse/llms and define your APIs.
@MinwooPark96. Thank you for your kindly help. Will you submit a pull request and I will merge it into the main branch.
@PeterSH6 I've merged the conflict/recommendation parts and updated them to the latest up-stream VeRL. Please kindly let me know if there are still issues. This code base supports AMD GPUs...
@zhaochenyang20 , actually @YangWang92 and I are working on this virtual memory management issue. vLLM part: https://github.com/vllm-project/vllm/pull/12695#issuecomment-2633919751 SGLang part: https://github.com/sgl-project/sglang/issues/5093#issuecomment-2785084577 https://github.com/fzyzcjy/torch_memory_saver/issues/9#issuecomment-2850012653 Once we resolve the issues above, this problem will...
> I was the original author of [vllm-project/vllm#12695](https://github.com/vllm-project/vllm/pull/12695), and I've been following your progress after I found out about the issue for supporting sleep mode on MI250x. It would be...
> @yushengsu-thu To the best of my knowledge, I'm not aware of different ROCm APIs for achieving the same feature, but this is definitely something that's worth considering, and I...
> @zhaochenyang20 @yushengsu-thu @eric-haibin-lin Any plan to merge this soon? New conflicts constantly arise, and I hope to have this quickly merged so that I don't need to spend time...
@soldni It's awesome. Appreciate!!