ZhiyiDanielSu comments

Repositories
Issues
Comments

Results 1 comments of


                                            ZhiyiDanielSu

How can we integrate the DeepGEMM Fp8 GEMM implementation in TE's block-wise scaling？

> > Hi Xin, > > Could we expect an ETA on this? > > See PR [#1559](https://github.com/NVIDIA/TransformerEngine/pull/1559). Note you will need CUDA 12.9 to run it because the groupwise/blockwise...