Skip to content

@z-lab Z Lab

Change the repository type filter

All

    Repositories list

    4 repositories

    • paroquant

      Public
      [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
      Python
      •
      MIT License
      •22•267•9•0•Updated May 7, 2026May 7, 2026

    • dflash

      Public
      DFlash: Block Diffusion for Flash Speculative Decoding
      Python
      •
      MIT License
      •271•4k•45•9•Updated May 6, 2026May 6, 2026

    • sparselora

      Public
      [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
      Python
      •
      MIT License
      •4•75•2•0•Updated Mar 10, 2026Mar 10, 2026

    • flash-colreduce

      Public
      Fast, memory-efficient attention column reduction (e.g., sum, mean, max)
      Python
      •
      MIT License
      •1•46•0•0•Updated Feb 10, 2026Feb 10, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.