GaoYuYang issues

Repositories
Issues
Comments

Results 2 issues of


                                            GaoYuYang

"Found duplicate region name" error when load onnx model

## Description i meet a error when i run trtexec to load my model i first trans my model from paddle2onnx and then use trtexec to load the onnx model...

triaged

[QUESTION] Does sglang support fp8 kvcache in ampere such like A100

I want to use kvcache quant in A800 . Just found sglang doesn't support int8 kv-cache. I wonder if sglang can support fp8 kv-cache int A100. I think the kv-quant...