Commit Graph

  • 68fc742572
    Merge pull request #36 from yz-tang/fix_setup_build Chenggang Zhao 2025-03-04 17:09:50 +0800
  • 6c59e0f40d fix setup build error when setuptools version is lower yz-tang 2025-03-04 16:53:00 +0800
  • 9b0dad8640 Add some notes for promotion Chenggang Zhao 2025-03-04 11:42:20 +0800
  • ded740f736
    Fix documentation of m_grouped_gemm_fp8_fp8_bf16_nt_contiguous in m_grouped_gemm.py Liang 2025-03-04 11:26:23 +0800
  • dff6bb6f0b Add some notes Chenggang Zhao 2025-03-03 11:35:52 +0800
  • 6d0fd7de41 support groupwise scaling for b zhengxuegui.0 2025-03-01 23:04:15 +0800
  • 261fff9c48 Specify uint8_t as enum size Colin Peppler 2025-02-27 21:16:35 -0800
  • 6c5da03ba9 Support more shapes Chenggang Zhao 2025-02-28 10:04:59 +0800
  • b69f630b91 Minor fix util function Chenggang Zhao 2025-02-28 09:46:38 +0800
  • 6e10cba207 Minor fix Chenggang Zhao 2025-02-28 09:21:35 +0800
  • b0b9e03345
    refactor the loop if/else check A-transformer 2025-02-27 22:23:53 +0400
  • 92521df34d
    comment more clear about Memory Consistency and Barrier Visibility A-transformer 2025-02-27 22:01:50 +0400
  • a2e0d68eed
    Merge pull request #2 from deepseek-ai/main A-transformer 2025-02-27 21:47:31 +0400
  • fbec9e5eee
    Update get_best_configs Liang 2025-02-27 23:18:52 +0800
  • 461427ecd0
    Merge pull request #27 from vatlor/main Zhean Xu 2025-02-27 20:37:31 +0800
  • 488b5fc467 fix typo dotrail 2025-02-27 11:53:33 +0000
  • b4d5f535bb
    pytest Integration A-transformer 2025-02-27 14:38:54 +0400
  • 6da94d2d36 Add extra TMA checks Chenggang Zhao 2025-02-27 18:20:57 +0800
  • ca13ce0fab Fix TMA store bugs and code format Chenggang Zhao 2025-02-27 17:57:21 +0800
  • 8933678ee5 upd BBuf 2025-02-27 17:21:18 +0800
  • 22c163be25
    pytest Integration A-transformer 2025-02-27 11:55:32 +0400
  • 60cce9a6e3
    pytest Integration A-transformer 2025-02-27 11:54:28 +0400
  • a813073fac
    pytest Integration A-transformer 2025-02-27 11:53:38 +0400
  • 5479ffebb0
    pytest Integration A-transformer 2025-02-27 11:44:52 +0400
  • f9a6da9ac2
    pytest Integration A-transformer 2025-02-27 11:43:23 +0400
  • 58046b4e01
    pytest Integration A-transformer 2025-02-27 09:48:20 +0400
  • b05ed2f017 Code format Chenggang Zhao 2025-02-27 10:50:20 +0800
  • 676329b8e2
    Merge pull request #19 from dzhulgakov/fix-wheel Chenggang Zhao 2025-02-27 10:44:11 +0800
  • 6e55da296f Fix python -O mode issues Chenggang Zhao 2025-02-27 10:42:46 +0800
  • d5b974da2b
    Merge pull request #16 from AcraeaTerpsicore/patch-1 Chenggang Zhao 2025-02-27 10:34:12 +0800
  • fc7c3f8299 setup.py: fix wheel building Dmytro Dzhulgakov 2025-02-26 17:48:57 +0000
  • 78cacf70d4
    Update README.md Zhean Xu 2025-02-26 19:20:39 +0800
  • 96b31fd6bb
    fix typo AcraeaTerpsicore 2025-02-26 18:37:22 +0800
  • bc989405fe fix: prevent expected_m from exceeding m in test_core xuzhean 2025-02-26 16:55:47 +0800
  • eec7ab7f03
    Merge pull request #13 from ZeppLu/patch-1 Zhean Xu 2025-02-26 16:34:23 +0800
  • 7a70b439cd
    doc: Use permanent link Zepp 2025-02-26 16:15:37 +0800
  • 184ce9b5ea
    Merge pull request #3 from acheong08/patch-1 Chenggang Zhao 2025-02-26 13:29:45 +0800
  • 5da24e229a
    spelling: README.md Antonio Cheong 2025-02-26 02:36:04 +0000
  • a6d97a1c1b Initial commit Chenggang Zhao 2025-02-25 22:52:41 +0800