Baizhou Zhang

[1/2] Refactor DeepGeem requant for FP8 Linear on Blackwell

2

## Motivation Co-Author: @fy1214 Based on pr: https://github.com/sgl-project/sglang/pull/13067 Refactor for MoE requant will be left to the next PR ## Modifications To run DeepGemm on Blackwell, the input scale factor...

[Feature] Add a FP8 Gemm backend for choosing FP8 gemm kernel

3

### Checklist - [ ] If this is not a feature request but a general question, please start a discussion at https://github.com/sgl-project/sglang/discussions. Otherwise, it will be closed. - [ ]...

## Motivation Relanding of #13341 Based on #13751 ## Modifications ## Accuracy Tests ## Benchmarking and Profiling ## Checklist - [ ] Format your code according to the [Format code...

[chore]Upgrade flashinfer to 0.5.3

2

## Motivation Close #13748 ## Modifications ## Accuracy Tests ## Benchmarking and Profiling ## Checklist - [ ] Format your code according to the [Format code with pre-commit](https://docs.sglang.ai/developer_guide/contribution_guide.html#format-code-with-pre-commit). - [...

[chore] Upgrade nvshmem/cublas/nccl for cu13 docker

1

## Motivation ## Modifications ## Accuracy Tests ## Benchmarking and Profiling ## Checklist - [ ] Format your code according to the [Format code with pre-commit](https://docs.sglang.ai/developer_guide/contribution_guide.html#format-code-with-pre-commit). - [ ] Add...

### Checklist - [ ] If this is not a feature request but a general question, please start a discussion at https://github.com/sgl-project/sglang/discussions. Otherwise, it will be closed. - [ ]...