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.
☆11Updated last year
Alternatives and similar repositories for AITemplate
Users that are interested in AITemplate are comparing it to the libraries listed below
Sorting:
- Development repository for the Triton language and compiler☆125Updated this week
- Fast and memory-efficient exact attention☆174Updated this week
- Ahead of Time (AOT) Triton Math Library☆67Updated last week
- AI Tensor Engine for ROCm☆208Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆84Updated this week
- OpenAI Triton backend for Intel® GPUs☆191Updated this week
- ☆38Updated this week
- a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA en…☆43Updated 10 months ago
- [DEPRECATED] Moved to ROCm/rocm-libraries repo☆106Updated this week
- ☆25Updated last week
- ☆212Updated 11 months ago
- rocWMMA☆117Updated this week
- oneCCL Bindings for Pytorch*☆97Updated 2 months ago
- ☆117Updated last month
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 11 months ago
- ☆48Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆252Updated 8 months ago
- A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch☆22Updated this week
- ☆62Updated 6 months ago
- Test suite for probing the numerical behavior of NVIDIA tensor cores☆40Updated 11 months ago
- A CUTLASS implementation using SYCL☆27Updated this week
- Intel® Extension for DeepSpeed* is an extension to DeepSpeed that brings feature support with SYCL kernels on Intel GPU(XPU) device. Note…☆61Updated last week
- Github mirror of trition-lang/triton repo.☆39Updated last week
- An extension library of WMMA API (Tensor Core API)☆99Updated 11 months ago
- ROCm Communication Collectives Library (RCCL)☆343Updated this week
- collection of benchmarks to measure basic GPU capabilities☆385Updated 4 months ago
- A Quirky Assortment of CuTe Kernels☆117Updated this week
- A tool for generating information about the matrix multiplication instructions in AMD Radeon™ and AMD Instinct™ accelerators☆102Updated last month
- 8-bit CUDA functions for PyTorch☆53Updated last week
- ROC profiler library. Profiling with perf-counters and derived metrics.☆148Updated last week