1. 23 Oct, 2025 2 commits
    • zhuwenwen's avatar
      update test_moe.py · 86d92eb9
      zhuwenwen authored
      set USE_FUSED_RMS_QUANT=1 and USE_FUSED_SILU_MUL_QUANT=1
      86d92eb9
    • zhuwenwen's avatar
      support prefix cache on kme · 6f1db287
      zhuwenwen authored
      fix the error in test_moe caused by moe align not supporting 511
      multi-modal switching to torch implementation on z100l&k100
      6f1db287
  2. 17 Oct, 2025 1 commit
  3. 15 Oct, 2025 2 commits
  4. 13 Oct, 2025 6 commits
  5. 11 Oct, 2025 1 commit
  6. 10 Oct, 2025 1 commit
  7. 05 Oct, 2025 2 commits
  8. 29 Sep, 2025 1 commit
  9. 26 Sep, 2025 4 commits
  10. 25 Sep, 2025 3 commits
  11. 24 Sep, 2025 2 commits
  12. 23 Sep, 2025 1 commit
  13. 22 Sep, 2025 1 commit
  14. 15 Sep, 2025 1 commit
  15. 14 Sep, 2025 1 commit
  16. 11 Sep, 2025 2 commits
  17. 10 Sep, 2025 1 commit
  18. 09 Sep, 2025 3 commits
  19. 08 Sep, 2025 1 commit
  20. 07 Sep, 2025 2 commits
  21. 04 Sep, 2025 1 commit
  22. 03 Sep, 2025 1 commit