openai / blocksparse
Efficient GPU kernels for block-sparse matrix multiplication and convolution
☆1,038Updated last year
Alternatives and similar repositories for blocksparse:
Users that are interested in blocksparse are comparing it to the libraries listed below
- ATen: A TENsor library for C++11☆695Updated 5 years ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,293Updated this week
- Fast Block Sparse Matrices for Pytorch☆545Updated 4 years ago
- Tutorial for building a custom CUDA function for Pytorch☆511Updated 6 years ago
- PyTorch elastic training☆730Updated 2 years ago
- Collective communications library with various primitives for multi-machine training.☆1,288Updated this week
- A domain specific language to express machine learning workloads.☆1,759Updated last year
- TVM integration into PyTorch☆452Updated 5 years ago
- A GPU performance profiling tool for PyTorch models☆505Updated 3 years ago
- A GPipe implementation in PyTorch☆835Updated 8 months ago
- common in-memory tensor structure☆974Updated this week
- The Tensor Algebra SuperOptimizer for Deep Learning☆705Updated 2 years ago
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,564Updated 4 years ago
- Mesh TensorFlow: Model Parallelism Made Easier☆1,605Updated last year
- Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/…☆394Updated 6 years ago
- Open single and half precision gemm implementations☆379Updated 2 years ago
- Low-precision matrix multiplication☆1,798Updated last year
- [ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing☆331Updated 9 months ago
- C++ extensions in PyTorch☆1,079Updated 2 months ago
- PyTorch C++ API Documentation☆222Updated this week
- A library of GPU kernels for sparse matrix operations.☆262Updated 4 years ago
- A tensor-aware point-to-point communication primitive for machine learning☆256Updated 2 years ago
- Library for faster pinned CPU <-> GPU transfer in Pytorch☆686Updated 5 years ago
- Automatic differentiation with weighted finite-state transducers.☆455Updated 3 years ago
- A simple memory manager for CUDA designed to help Deep Learning frameworks manage memory☆297Updated 6 years ago
- PyTorch layer-by-layer model profiler☆606Updated 3 years ago
- Block-sparse primitives for PyTorch☆154Updated 4 years ago
- Benchmarking Deep Learning operations on different hardware☆1,082Updated 3 years ago
- A CUDNN minimal deep learning training code sample using LeNet.☆264Updated last year
- Dive into Deep Learning Compiler☆646Updated 2 years ago