openai / blocksparseLinks
Efficient GPU kernels for block-sparse matrix multiplication and convolution
☆1,043Updated 2 years ago
Alternatives and similar repositories for blocksparse
Users that are interested in blocksparse are comparing it to the libraries listed below
Sorting:
- ATen: A TENsor library for C++11☆699Updated 5 years ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,399Updated this week
- A GPipe implementation in PyTorch☆844Updated 11 months ago
- A GPU performance profiling tool for PyTorch models☆503Updated 3 years ago
- Mesh TensorFlow: Model Parallelism Made Easier☆1,612Updated last year
- A domain specific language to express machine learning workloads.☆1,759Updated 2 years ago
- Fast Block Sparse Matrices for Pytorch☆548Updated 4 years ago
- C++ extensions in PyTorch☆1,113Updated this week
- The Tensor Algebra SuperOptimizer for Deep Learning☆719Updated 2 years ago
- Guide for building custom op for TensorFlow☆382Updated 2 years ago
- Tutorial for building a custom CUDA function for Pytorch☆517Updated 6 years ago
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,579Updated 4 years ago
- Collective communications library with various primitives for multi-machine training.☆1,326Updated 3 weeks ago
- TVM integration into PyTorch☆453Updated 5 years ago
- Library for faster pinned CPU <-> GPU transfer in Pytorch☆685Updated 5 years ago
- ☆586Updated 7 years ago
- Benchmarking Deep Learning operations on different hardware☆1,089Updated 4 years ago
- Block-sparse primitives for PyTorch☆157Updated 4 years ago
- PyTorch elastic training☆728Updated 3 years ago
- common in-memory tensor structure☆1,026Updated last month
- Open single and half precision gemm implementations☆381Updated 2 years ago
- A performant and modular runtime for TensorFlow☆758Updated 2 months ago
- TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.☆959Updated last week
- A tensor-aware point-to-point communication primitive for machine learning☆259Updated 2 years ago
- Make huge neural nets fit in memory☆2,800Updated 5 years ago
- A library of GPU kernels for sparse matrix operations.☆270Updated 4 years ago
- Experimental ground for optimizing memory of pytorch models☆366Updated 7 years ago
- PyTorch layer-by-layer model profiler☆607Updated 4 years ago
- Myia prototyping☆457Updated last year
- A pedagogical implementation of Autograd☆986Updated 5 years ago