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++ 111 15

3. BitDecoding-FP4 BitDecoding-FP4 Public

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

   Python 35 1

4. vlut.cpp vlut.cpp Public

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

   C++ 28 5