tgale96/grouped_gemm

Issues

• Installation issue

  #24 opened 14 days ago by jayjk13
  2

• Overhead of setting workspace?

  #23 opened 15 days ago by chenhongyu2048
  0

• Why require torch>= 2.4？I want to use it with 2.0 or 2.1

  #22 opened 18 days ago by LamForest
  0

• Installation issues with grouped gemm

  #20 opened 2 months ago by snarayan21
  1

• does grouped gemm support float16?

  #19 opened 2 months ago by blankde
  0

• Composing grouped gemms leads to precision loss

  #17 opened 3 months ago by kiddyboots216
  1

• Errors when running on other cuda devices

  #15 opened 3 months ago by Oasis-Git
  3

• What is the difference with GroupedGemm of Cutlass

  #13 opened 9 months ago by GuWei007
  1

• Grouped GEMM Execution not possible with HW

  #4 opened 10 months ago by ryandeng1
  3

• Why cannot support transposition of matrix B with CUTLASS GroupedGEMM?

  #3 opened a year ago by fanshiqing
  2

• License request for this repo.

  #2 opened a year ago by fanshiqing
  2

• Loss diverges at the 3rd training step between GroupedGEMM and Sequential GEMMs

  #1 opened a year ago by fanshiqing
  5