Skip to content
@OpenBitSys

OpenBitSys

Popular repositories Loading

  1. BitDistiller BitDistiller Public

    [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.

    Python 142 20

  2. BitDecoding BitDecoding Public

    [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.

    C++ 113 16

  3. BitDecoding-FP4 BitDecoding-FP4 Public

    Accurate, fast FP4 KV-cache decoding through algorithm-system co-design.

    Python 39 2

  4. vlut.cpp vlut.cpp Public

    [MobiSys 2026] On-device ultra-low-bit LLM inference with LUT

    C++ 29 5

Repositories

Showing 4 of 4 repositories
  • BitDecoding-FP4 Public

    Accurate, fast FP4 KV-cache decoding through algorithm-system co-design.

    OpenBitSys/BitDecoding-FP4's past year of commit activity
    Python 39 MIT 2 0 0 Updated Nov 9, 2026
  • BitDecoding Public

    [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.

    OpenBitSys/BitDecoding's past year of commit activity
    C++ 113 MIT 16 5 0 Updated Nov 3, 2026
  • vlut.cpp Public

    [MobiSys 2026] On-device ultra-low-bit LLM inference with LUT

    OpenBitSys/vlut.cpp's past year of commit activity
    C++ 29 MIT 5 0 0 Updated Jun 24, 2026
  • BitDistiller Public

    [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.

    OpenBitSys/BitDistiller's past year of commit activity
    Python 142 MIT 20 10 0 Updated May 16, 2024

Top languages

Loading…