NVIDIA / jaxppLinks
JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training
☆52Updated 2 weeks ago
Alternatives and similar repositories for jaxpp
Users that are interested in jaxpp are comparing it to the libraries listed below
Sorting:
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆271Updated this week
- extensible collectives library in triton☆88Updated 4 months ago
- ☆232Updated last week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆207Updated this week
- A Quirky Assortment of CuTe Kernels☆411Updated this week
- Collection of kernels written in Triton language☆147Updated 4 months ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- ☆88Updated 9 months ago
- Applied AI experiments and examples for PyTorch☆291Updated this week
- TritonParse: A Compiler Tracer, Visualizer, and mini-Reproducer(WIP) for Triton Kernels☆144Updated this week
- A library to analyze PyTorch traces.☆404Updated last week
- Cataloging released Triton kernels.☆252Updated 7 months ago
- Fast low-bit matmul kernels in Triton☆353Updated last week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆208Updated last week
- ring-attention experiments☆149Updated 10 months ago
- ☆115Updated 5 months ago
- ☆172Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆110Updated 2 months ago
- ☆229Updated last year
- A bunch of kernels that might make stuff slower 😉☆58Updated last week
- ☆111Updated 8 months ago
- Fastest kernels written from scratch☆316Updated 4 months ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆120Updated 9 months ago
- kernels, of the mega variety☆476Updated 2 months ago
- ☆110Updated last year
- ☆28Updated 7 months ago
- Ahead of Time (AOT) Triton Math Library☆75Updated this week
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆209Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆537Updated this week