1. 19 Dec, 2025 1 commit
  2. 18 Dec, 2025 1 commit
  3. 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
  4. 12 Dec, 2025 1 commit
  5. 11 Dec, 2025 1 commit
  6. 08 Dec, 2025 1 commit
  7. 02 Dec, 2025 3 commits
  8. 30 Nov, 2025 1 commit
  9. 26 Nov, 2025 1 commit
  10. 24 Nov, 2025 1 commit
  11. 20 Nov, 2025 2 commits
  12. 19 Nov, 2025 3 commits
  13. 15 Nov, 2025 1 commit
  14. 13 Nov, 2025 2 commits
  15. 10 Nov, 2025 1 commit
  16. 08 Nov, 2025 1 commit
  17. 06 Nov, 2025 1 commit
  18. 05 Nov, 2025 1 commit
  19. 31 Oct, 2025 1 commit
  20. 21 Oct, 2025 4 commits
  21. 18 Oct, 2025 2 commits
  22. 16 Oct, 2025 1 commit
  23. 15 Oct, 2025 2 commits
  24. 12 Oct, 2025 1 commit
  25. 11 Oct, 2025 1 commit
  26. 09 Oct, 2025 2 commits
  27. 07 Oct, 2025 1 commit
  28. 06 Oct, 2025 1 commit