Discussions: NVIDIA/cutlass

Discussions

• 1 You must be logged in to vote

  🙏

  HFMA2 and LDS in cutlass efficient fp16 tensorcore kernel?

  LeiWang1999 asked Dec 1, 2022 in Q&A · Answered

  

  

  

  

  3
• 1 You must be logged in to vote

  🙏

  Vectorized epilogue in v3 API

  masahi asked Feb 13, 2023 in Q&A · Answered

  

  

  

  

  3
• 1 You must be logged in to vote

  💬

  How to select SparseGemm template arguments?

  cgorac started Feb 13, 2023 in General

  

  

  7
• 4 You must be logged in to vote

  🙏

  Allowing "source" (bias tensor) and output tensor to have different data type

  masahi asked Nov 1, 2021 in Q&A · Answered

  

  

  

  

  5
• 4 You must be logged in to vote

  💬

  CUTLASS 3.0 is now available!

  thakkarV started Jan 24, 2023 in General

  

  

  0
• 1 You must be logged in to vote

  💬

  NOTICE: Please be aware of an upcoming modification to our fMHA

  mnicely started Jan 19, 2023 in General

  

  

  0
• 1 You must be logged in to vote

  💬

  Large standard deviation when profile cutlass profiler with nsys profiler.

  Quangnguyengiabku started Dec 28, 2022 in General

  

  

  1
• 1 You must be logged in to vote

  🙏

  Confused with the inst size shown in Profiler log

  Adnios asked Dec 11, 2022 in Q&A · Answered

  

  

  2
• 1 You must be logged in to vote

  🙏

  Questions about GemmWithReduceK

  Enter-tainer asked Dec 6, 2022 in Q&A · Answered

  

  

  

  

  5
• 1 You must be logged in to vote

  🙏

  Does gemm-streamk has stricter alignment requirement than normal gemm?

  lygztq asked Dec 6, 2022 in Q&A · Answered

  

  

  2
• 4 You must be logged in to vote

  💬

  CUTLASS 2.11 now available!

  mnicely started Nov 20, 2022 in General

  

  

  2
• 1 You must be logged in to vote

  🙏

  Gemm Fused Row Reduction question.

  MARD1NO asked Nov 28, 2022 in Q&A · Answered

  

  

  1
• 1 You must be logged in to vote

  🙏

  How to tune cutlass matmul kernels to approach cublasLt one?

  MARD1NO asked Nov 16, 2022 in Q&A · Answered

  

  

  4
• 1 You must be logged in to vote

  💬

  CUTLASS in RAFT

  mnicely started Nov 20, 2022 in General

  

  

  1
• 2 You must be logged in to vote

  💬

  CUTLASS is integrated into Oneflow to use fMHA

  hwu36 started Nov 14, 2022 in General

  

  

  0
• 1 You must be logged in to vote

  💬

  CUTLASS in PaddlePaddle

  hwu36 started Nov 7, 2022 in General

  

  

  1
• 1 You must be logged in to vote

  💬

  CUTLASS hits 3M dowaloads

  hwu36 started Oct 31, 2022 in General

  

  

  0
• 1 You must be logged in to vote

  💬

  CUTLASS is in Alibaba NMM

  hwu36 started Sep 28, 2022 in General

  

  

  1
• 1 You must be logged in to vote

  💬

  CUTLASS is added into pytorch as a 3rd party library

  hwu36 started Oct 24, 2022 in General

  

  

  0
• 1 You must be logged in to vote

  🙏

  Why cutlass don't have nn layout gemm for int8 tensorcore?

  LeiWang1999 asked Sep 27, 2022 in Q&A · Answered

  

  

  

  

  3
• 1 You must be logged in to vote

  🙏

  Confused about cutlass layout

  LeiWang1999 asked Oct 18, 2022 in Q&A · Answered

  

  

  5
• 1 You must be logged in to vote

  💬

  Meta's xFormers has Attention kernel written in CUTLASS

  hwu36 started Oct 10, 2022 in General

  

  

  

  

  10
• 1 You must be logged in to vote

  🙏

  Shared memory bank conflict problem

  FindDefinition asked Jun 17, 2021 in Q&A · Unanswered

  

  

  

  

  7
• 1 You must be logged in to vote

  🙏

  How CUTLASS deal with the last mma tile

  zihaozou asked Aug 3, 2022 in Q&A · Answered

  

  

  

  

  16
• 3 You must be logged in to vote

  💬

  NVCC 11.8 is out

  hwu36 started Oct 4, 2022 in General

  

  

  0