1. 29 Nov, 2022 1 commit
  2. 24 Nov, 2022 1 commit
  3. 03 Oct, 2022 1 commit
    • Jeff Daily's avatar
      enable ROCm build; add BF16 for ROCm and CUDA (#325) · 9a651d91
      Jeff Daily authored
      * first step, everything compiles
      
      * fix rebuilds; skip cuda version check for rocm
      
      * use macro for __shfl_up_sync __shfl_down_sync
      
      * add BFloat16 support for ROCm and CUDA
      
      * add USE_ROCM definition to setup.py
      
      * flake8 fixes
      9a651d91
  4. 25 Mar, 2022 1 commit
  5. 07 Nov, 2021 1 commit
  6. 22 Oct, 2021 3 commits
  7. 13 Sep, 2021 1 commit
  8. 07 Sep, 2021 1 commit
  9. 24 Aug, 2021 1 commit
  10. 11 Aug, 2021 1 commit
  11. 05 Aug, 2021 1 commit
  12. 28 Jul, 2021 1 commit
  13. 19 Jul, 2021 2 commits
  14. 05 Jun, 2021 1 commit
  15. 11 May, 2021 1 commit
  16. 25 Mar, 2021 1 commit
  17. 02 Mar, 2021 3 commits
  18. 19 Jan, 2021 2 commits
  19. 15 Jan, 2021 1 commit
  20. 12 Jan, 2021 1 commit
  21. 03 Jan, 2021 1 commit
  22. 11 Dec, 2020 1 commit
  23. 07 Aug, 2020 1 commit
  24. 18 Jul, 2020 2 commits
  25. 24 Jun, 2020 1 commit
  26. 12 Jun, 2020 1 commit
  27. 23 Apr, 2020 3 commits
  28. 06 Apr, 2020 1 commit
  29. 02 Apr, 2020 1 commit
  30. 01 Apr, 2020 1 commit
  31. 22 Feb, 2020 1 commit