Weihang Wang

按照博主的接口去请求，最后得到的obj_resp好像改了，麻烦博主看一下！

tokens routing

6

thanks for your work! It is very valuable! I would like to know how you got your conclusion about token routing, since input is affected by attention and rope, it...

About In-batch debiased cross-entropy loss

2

Which article proposed In-batch debiased cross-entropy loss? Can you provide relevant literature?

Vllm v0.11.0, Qwen3-VL-235B(-FP8) deployed on 8 A100s OOM

6

My vllm version is 0.11.0. I deployed it according to the official recommended command: ``` vllm serve Qwen/Qwen3-VL-235B-A22B-Instruct \ --tensor-parallel-size 8 \ --max-model-len 128000 \ --async-scheduling \ --enable-expert-parallel ``` I...