1. 06 Jan, 2026 2 commits
  2. 19 Dec, 2025 1 commit
  3. 18 Dec, 2025 1 commit
  4. 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
  5. 12 Dec, 2025 1 commit
  6. 11 Dec, 2025 1 commit
  7. 08 Dec, 2025 1 commit
  8. 02 Dec, 2025 3 commits
  9. 30 Nov, 2025 1 commit
  10. 26 Nov, 2025 1 commit
  11. 24 Nov, 2025 1 commit
  12. 20 Nov, 2025 2 commits
  13. 19 Nov, 2025 3 commits
  14. 15 Nov, 2025 1 commit
  15. 13 Nov, 2025 2 commits
  16. 10 Nov, 2025 1 commit
  17. 08 Nov, 2025 1 commit
  18. 06 Nov, 2025 1 commit
  19. 05 Nov, 2025 1 commit
  20. 31 Oct, 2025 1 commit
  21. 21 Oct, 2025 4 commits
  22. 18 Oct, 2025 2 commits
  23. 16 Oct, 2025 1 commit
  24. 15 Oct, 2025 2 commits
  25. 12 Oct, 2025 1 commit
  26. 11 Oct, 2025 1 commit
  27. 09 Oct, 2025 2 commits