IST-DASLab / gemm-int8Links
High Performance Int8 GEMM Kernels for SM80 and later GPUs.
☆18Updated 10 months ago
Alternatives and similar repositories for gemm-int8
Users that are interested in gemm-int8 are comparing it to the libraries listed below
Sorting:
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆20Updated last year
- Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”☆116Updated this week
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆172Updated 2 months ago
- ☆60Updated last year
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆207Updated 2 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆80Updated 6 months ago
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆68Updated last year
- ☆84Updated last year
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆50Updated 2 years ago
- ☆170Updated 2 years ago
- ☆93Updated 2 months ago
- [ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitt…☆88Updated 9 months ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆67Updated 6 months ago
- DeeperGEMM: crazy optimized version☆73Updated 8 months ago
- Code Repository of Evaluating Quantized Large Language Models☆136Updated last year
- This repository contains integer operators on GPUs for PyTorch.☆236Updated 2 years ago
- Official implementation of the ICLR 2024 paper AffineQuant☆28Updated last year
- ☆40Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆279Updated 3 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆154Updated 5 months ago
- ☆84Updated last year
- ☆65Updated 9 months ago
- ☆77Updated last year
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆165Updated 2 months ago
- ☆105Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆123Updated 6 months ago
- A quantization algorithm for LLM☆148Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆110Updated 9 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Updated 4 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆141Updated 8 months ago