IST Austria Distributed Algorithms and Systems Lab (original) (raw)
Popular repositories Loading
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
Python 2.1k 167
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
Python 817 66
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".
Python 791 102
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
Python 274 21
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024
C++ 180 13