ROCm / aiterLinks
AI Tensor Engine for ROCm
☆201Updated this week
Alternatives and similar repositories for aiter
Users that are interested in aiter are comparing it to the libraries listed below
Sorting:
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators☆400Updated this week
- Development repository for the Triton language and compiler☆122Updated this week
- OpenAI Triton backend for Intel® GPUs☆187Updated this week
- Ahead of Time (AOT) Triton Math Library☆64Updated this week
- Perplexity GPU Kernels☆324Updated last week
- An experimental CPU backend for Triton☆118Updated last month
- Stretching GPU performance for GEMMs and tensor contractions.☆242Updated last week
- hipBLASLt is a library that provides general matrix-matrix operations with a flexible API and extends functionalities beyond a traditiona…☆97Updated this week
- RCCL Performance Benchmark Tests☆67Updated last week
- Fast low-bit matmul kernels in Triton☆303Updated last week
- Fast and memory-efficient exact attention☆172Updated this week
- rocWMMA☆114Updated this week
- Shared Middle-Layer for Triton Compilation☆251Updated this week
- ☆109Updated 3 weeks ago
- ☆86Updated 5 months ago
- ☆146Updated this week
- ☆206Updated 10 months ago
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆95Updated last week
- ROCm Communication Collectives Library (RCCL)☆337Updated this week
- Experimental projects related to TensorRT☆105Updated this week
- Unified compiler/runtime for interfacing with PyTorch Dynamo.☆100Updated 2 weeks ago
- AMD's graph optimization engine.☆220Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆251Updated 7 months ago
- ☆24Updated 3 weeks ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆365Updated this week
- QuickReduce is a performant all-reduce library designed for AMD ROCm that supports inline compression.☆27Updated 2 months ago
- amdgpu example code in hip/asm☆32Updated last week
- ☆36Updated this week
- A lightweight design for computation-communication overlap.☆132Updated 3 weeks ago
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆169Updated this week