1. 18 Dec, 2025 3 commits
  2. 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
  3. 13 Dec, 2025 6 commits
  4. 05 Dec, 2025 4 commits
  5. 04 Dec, 2025 7 commits
  6. 03 Dec, 2025 5 commits
  7. 02 Dec, 2025 14 commits