NVIDIA / nccl
Optimized primitives for collective multi-GPU communication
☆3,253Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for nccl
- NCCL Tests☆898Updated 2 weeks ago
- Collective communications library with various primitives for multi-machine training.☆1,227Updated this week
- oneAPI Deep Neural Network Library (oneDNN)☆3,635Updated this week
- CUDA Templates for Linear Algebra Subroutines☆5,679Updated this week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,210Updated this week
- [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl☆1,684Updated last year
- A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology☆896Updated 2 weeks ago
- Reference implementations of MLPerf™ training benchmarks☆1,617Updated last month
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆1,979Updated this week
- Reference implementations of MLPerf™ inference benchmarks☆1,238Updated this week
- common in-memory tensor structure☆912Updated last month
- Low-precision matrix multiplication☆1,780Updated 9 months ago
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆2,710Updated this week
- PyTorch extensions for high performance and large scale training.☆3,195Updated last week
- A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep lear…☆5,158Updated this week
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆11,798Updated this week
- A benchmark framework for Tensorflow☆1,150Updated last year
- Enabling PyTorch on XLA Devices (e.g. Google TPU)☆2,489Updated this week
- A domain specific language to express machine learning workloads.☆1,761Updated last year
- Open MPI main development repository☆2,172Updated this week
- ☆568Updated 6 years ago
- Compiler for Neural Network hardware accelerators☆3,236Updated 6 months ago
- CUDA Library Samples☆1,617Updated this week
- Acceleration package for neural networks on multi-core CPUs☆1,676Updated 5 months ago
- Source code examples from the Parallel Forall Blog☆1,239Updated 3 months ago
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆962Updated 2 months ago
- Benchmarking Deep Learning operations on different hardware☆1,074Updated 3 years ago
- Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)☆1,157Updated this week
- Samples for CUDA Developers which demonstrates features in CUDA Toolkit☆6,458Updated 3 months ago
- A high performance and generic framework for distributed DNN training☆3,630Updated last year