ROCm / AITemplateLinks
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
☆12Updated last year
Alternatives and similar repositories for AITemplate
Users that are interested in AITemplate are comparing it to the libraries listed below
Sorting:
- Fast and memory-efficient exact attention☆191Updated this week
- Development repository for the Triton language and compiler☆133Updated this week
- AI Tensor Engine for ROCm☆284Updated this week
- ☆47Updated this week
- Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators☆470Updated this week
- ☆27Updated last week
- OpenAI Triton backend for Intel® GPUs☆210Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆103Updated this week
- Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note…☆63Updated 3 months ago
- Ahead of Time (AOT) Triton Math Library☆77Updated this week
- QuickReduce is a performant all-reduce library designed for AMD ROCm that supports inline compression.☆33Updated last month
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- SYCL* Templates for Linear Algebra (SYCL*TLA) - SYCL based CUTLASS implementation for Intel GPUs☆40Updated this week
- monorepo for rocm libraries☆132Updated this week
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆23Updated this week
- AMD's graph optimization engine.☆253Updated this week
- a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA en…☆48Updated last year
- 8-bit CUDA functions for PyTorch☆63Updated 2 weeks ago
- ☆238Updated last year
- ☆148Updated 5 months ago
- ☆57Updated this week
- rocWMMA☆133Updated this week
- [DEPRECATED] Moved to ROCm/rocm-libraries repo☆111Updated this week
- ROCm Communication Collectives Library (RCCL)☆386Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆685Updated 2 months ago
- ☆63Updated 9 months ago
- collection of benchmarks to measure basic GPU capabilities☆427Updated 7 months ago
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆623Updated 3 weeks ago
- oneCCL Bindings for Pytorch*☆102Updated 2 months ago
- Experimental projects related to TensorRT☆112Updated last week