1. 06 Feb, 2026 1 commit
  2. 26 Jan, 2026 1 commit
  3. 24 Jan, 2026 1 commit
  4. 21 Jan, 2026 1 commit
  5. 16 Jan, 2026 1 commit
  6. 07 Jan, 2026 1 commit
  7. 06 Jan, 2026 1 commit
  8. 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
  9. 11 Dec, 2025 1 commit
  10. 10 Dec, 2025 1 commit
  11. 26 Nov, 2025 1 commit
  12. 19 Nov, 2025 1 commit
  13. 13 Nov, 2025 2 commits
  14. 10 Nov, 2025 1 commit
  15. 05 Nov, 2025 1 commit
  16. 12 Oct, 2025 1 commit
  17. 11 Oct, 2025 2 commits
  18. 05 Oct, 2025 1 commit
  19. 28 Sep, 2025 3 commits
  20. 27 Sep, 2025 1 commit
  21. 26 Sep, 2025 1 commit
  22. 21 Sep, 2025 1 commit
  23. 17 Sep, 2025 3 commits
  24. 13 Sep, 2025 1 commit
  25. 12 Sep, 2025 1 commit
  26. 01 Sep, 2025 1 commit
  27. 29 Aug, 2025 1 commit
  28. 25 Aug, 2025 1 commit
  29. 20 Aug, 2025 1 commit
  30. 19 Aug, 2025 1 commit
  31. 13 Aug, 2025 1 commit
  32. 12 Aug, 2025 1 commit
  33. 11 Aug, 2025 1 commit
  34. 09 Aug, 2025 1 commit