TransferBench

TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)

最近更新: 10天前

triton

Development repository for the Triton language and compiler

最近更新: 10天前

composable_kernel_remove

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

最近更新: 10天前

hipfort

Fortran interfaces for ROCm libraries

最近更新: 10天前

ucx

Unified Communication Library X

最近更新: 10天前

hipSPARSE

ROCm SPARSE marshalling library

最近更新: 10天前

AMDMIGraphX

AMD's graph optimization engine.

最近更新: 10天前

tensorflow-upstream

TensorFlow ROCm port

最近更新: 10天前

rocPRIM

[DEPRECATED] Moved to ROCm/rocm-libraries repo

最近更新: 10天前

hipBLAS

ROCm BLAS marshalling library

最近更新: 10天前

Megatron-LM

Ongoing research training transformer models at scale

最近更新: 12天前

flash-attention

Fast and memory-efficient exact attention

最近更新: 12天前

ompi

Copy of the Open MPI repository

最近更新: 12天前

FBGEMM

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

最近更新: 12天前

vision

Datasets, Transforms and Models specific to Computer Vision

最近更新: 12天前

composable_kernel

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

最近更新: 12天前

cupy

A NumPy-compatible array library accelerated by CUDA

最近更新: 12天前

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

最近更新: 12天前

onnxruntime

ONNX Runtime: cross-platform, high performance scoring engine for ML models

最近更新: 12天前

rccl-tests

RCCL Performance Benchmark Tests

最近更新: 12天前
成就
2
Star
2
Fork
成员(1)
镜像

搜索帮助