Fengqing Jiang comments

Results 6 comments of


                                            Fengqing Jiang

Frequent request timed out error

Quite the same problem for me since midnight when I used "gpt-4-0314". It worked well before I went to sleep, but most of the stuff timeout today

<BlockedReason.OTHER: 2> with simple questions

I have kind of similar issue with palm text model. Any fix for this problem?

Any support for peft methods on PPO?

Interesting in the process on development for lora + ppo!

[Qwen-image-edit] Batch Inference Issue / Feature Request

Thank you very much for your help! I went through your fix, but I am not sure if that is same as I expected. As this can support multiple-image as...

[Qwen-image-edit] Batch Inference Issue / Feature Request

Thank you very much @yiyixuxu. Maybe this can be feature request expect for potential support.

[Feature] Support General Reward Model

@zhaochenyang20 Just wonder any update for this feature, seems like vllm team did not work on this, so really hope there could be some support from SGLang team