Efficient GPU kernels for block-sparse matrix multiplication and convolution
☆1,064Jun 8, 2023Updated 2 years ago
Alternatives and similar repositories for blocksparse
Users that are interested in blocksparse are comparing it to the libraries listed below
Sorting:
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,611Aug 12, 2020Updated 5 years ago
- Block-sparse primitives for PyTorch☆158Apr 5, 2021Updated 4 years ago
- Fast Block Sparse Matrices for Pytorch☆549Jan 21, 2021Updated 5 years ago
- A library of GPU kernels for sparse matrix operations.☆283Nov 24, 2020Updated 5 years ago
- CUDA templates for tile-sparse matrix multiplication based on CUTLASS.☆50Mar 1, 2018Updated 8 years ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,442Updated this week
- A domain specific language to express machine learning workloads.☆1,764Apr 28, 2023Updated 2 years ago
- Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.☆132Apr 24, 2023Updated 2 years ago
- Open single and half precision gemm implementations☆397Apr 2, 2023Updated 2 years ago
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆8,936Updated this week
- Transformer training code for sequential tasks☆609Sep 14, 2021Updated 4 years ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,543Updated this week
- Low-precision matrix multiplication☆1,832Jan 29, 2024Updated 2 years ago
- The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs☆1,350Apr 14, 2025Updated 11 months ago
- Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)☆2,112Jan 4, 2022Updated 4 years ago
- PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM☆1,264Feb 12, 2022Updated 4 years ago
- Assembler for NVIDIA Maxwell architecture☆1,059Jan 3, 2023Updated 3 years ago
- PyTorch extensions for high performance and large scale training.☆3,403Apr 26, 2025Updated 10 months ago
- Development repository for the Triton language and compiler☆18,656Mar 14, 2026Updated last week
- A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep lear…☆5,642Mar 13, 2026Updated last week
- Optimized primitives for collective multi-GPU communication☆4,531Updated this week
- Compiler for Neural Network hardware accelerators☆3,326May 11, 2024Updated last year
- Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.☆14,679Dec 1, 2025Updated 3 months ago
- Open Machine Learning Compiler Framework☆13,197Updated this week
- Chef cookbooks for managing a Ceph cluster☆12Apr 2, 2023Updated 2 years ago
- A GPipe implementation in PyTorch☆862Jul 25, 2024Updated last year
- Demos, pretrained models, and (WIP) code supporting Representation Mixing☆51Dec 18, 2018Updated 7 years ago
- An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.☆400Mar 11, 2023Updated 3 years ago
- Code and model for the paper "Improving Language Understanding by Generative Pre-Training"☆2,283Jan 25, 2019Updated 7 years ago
- Lingvo☆2,857Updated this week
- [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl☆1,821Oct 9, 2023Updated 2 years ago
- Make huge neural nets fit in memory☆2,834Apr 26, 2020Updated 5 years ago
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more☆35,108Updated this week
- Training Very Deep Neural Networks Without Skip-Connections☆589Jun 9, 2018Updated 7 years ago
- Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"☆3,182Jul 23, 2024Updated last year
- Ongoing research training transformer models at scale☆15,744Updated this week
- A Pytorch implementation of "FloWaveNet: A Generative Flow for Raw Audio"☆490Apr 23, 2019Updated 6 years ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆1,003Sep 19, 2024Updated last year
- PyTorch code for the "Deep Neural Networks with Box Convolutions" paper☆509Jan 20, 2020Updated 6 years ago