1. 17 Dec, 2025 1 commit
    • zhuwenwen's avatar
      Synchronize the modifications from the 12th to the 17th: · b66c8e4b
      zhuwenwen authored
      修复CompressedTensorsLinearMethod中的w4a16的冲突问题
      feat(moe): add Marlin W16A16 fused MoE behind VLLM_USE_MARLIN_W16A16_MOE
      replace the fp8_mqa_logits and fp8_paged_mqa_logits interfaces in deepgemm with mqa_logits and paged_mqa_logits from lightop
      b66c8e4b
  2. 26 Nov, 2025 1 commit
  3. 19 Nov, 2025 1 commit
  4. 13 Nov, 2025 2 commits
  5. 10 Nov, 2025 1 commit
  6. 05 Nov, 2025 1 commit
  7. 12 Oct, 2025 1 commit
  8. 11 Oct, 2025 2 commits
  9. 05 Oct, 2025 1 commit
  10. 28 Sep, 2025 3 commits
  11. 27 Sep, 2025 1 commit
  12. 26 Sep, 2025 1 commit
  13. 21 Sep, 2025 1 commit
  14. 17 Sep, 2025 3 commits
  15. 13 Sep, 2025 1 commit
  16. 12 Sep, 2025 1 commit
  17. 01 Sep, 2025 1 commit
  18. 29 Aug, 2025 1 commit
  19. 25 Aug, 2025 1 commit
  20. 20 Aug, 2025 1 commit
  21. 19 Aug, 2025 1 commit
  22. 13 Aug, 2025 1 commit
  23. 12 Aug, 2025 1 commit
  24. 11 Aug, 2025 1 commit
  25. 09 Aug, 2025 1 commit
  26. 08 Aug, 2025 1 commit
  27. 07 Aug, 2025 1 commit
  28. 30 Jul, 2025 1 commit
  29. 17 Jul, 2025 1 commit
  30. 14 Jul, 2025 1 commit
  31. 12 Jul, 2025 1 commit
  32. 11 Jul, 2025 2 commits
  33. 10 Jul, 2025 1 commit