Pinned Loading

1. IST-DASLab/gptq IST-DASLab/gptq Public

   Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

   Python 2.1k 171

2. IST-DASLab/sparsegpt IST-DASLab/sparsegpt Public

   Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

   Python 803 105

3. IST-DASLab/marlin IST-DASLab/marlin Public

   FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

   Python 835 67

4. IST-DASLab/qmoe IST-DASLab/qmoe Public

   Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".

   Python 276 21

5. IST-DASLab/OBC IST-DASLab/OBC Public

   Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".

   Python 120 15

6. rob-twophase rob-twophase Public

   The ultimate Rubik's Cube solving algorithm for high-speed axial robots.

   C++ 132 11