Skip to content
@z-lab

Z Lab

Efficient AI. PI: Zhijian Liu

Popular repositories Loading

  1. dflash dflash Public

    DFlash: Block Diffusion for Flash Speculative Decoding

    Python 1.8k 119

  2. paroquant paroquant Public

    [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

    Python 202 15

  3. sparselora sparselora Public

    [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

    Python 74 3

  4. flash-colreduce flash-colreduce Public

    Fast, memory-efficient attention column reduction (e.g., sum, mean, max)

    Python 45

Repositories

Showing 4 of 4 repositories
  • dflash Public

    DFlash: Block Diffusion for Flash Speculative Decoding

    z-lab/dflash’s past year of commit activity
    Python 1,825 MIT 119 29 1 Updated Apr 17, 2026
  • paroquant Public

    [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

    z-lab/paroquant’s past year of commit activity
    Python 202 MIT 15 11 0 Updated Apr 9, 2026
  • sparselora Public

    [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

    z-lab/sparselora’s past year of commit activity
    Python 74 MIT 3 2 0 Updated Mar 10, 2026
  • flash-colreduce Public

    Fast, memory-efficient attention column reduction (e.g., sum, mean, max)

    z-lab/flash-colreduce’s past year of commit activity
    Python 45 MIT 0 0 0 Updated Feb 10, 2026

Top languages

Python

Most used topics

Loading…