NVIDIA / jaxppLinks
JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training
☆57Updated last month
Alternatives and similar repositories for jaxpp
Users that are interested in jaxpp are comparing it to the libraries listed below
Sorting:
- extensible collectives library in triton☆91Updated 7 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆282Updated this week
- ☆247Updated this week
- Autonomous GPU Kernel Generation via Deep Agents☆123Updated this week
- Applied AI experiments and examples for PyTorch☆303Updated 2 months ago
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆171Updated this week
- ☆93Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆127Updated 5 months ago
- How to ensure correctness and ship LLM generated kernels in PyTorch☆117Updated this week
- Cataloging released Triton kernels.☆267Updated 2 months ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆620Updated this week
- This repository contains the experimental PyTorch native float8 training UX☆223Updated last year
- Fast low-bit matmul kernels in Triton☆395Updated 3 weeks ago
- Collection of kernels written in Triton language☆164Updated 7 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 4 months ago
- ring-attention experiments☆155Updated last year
- ☆243Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆85Updated 2 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆216Updated this week
- A bunch of kernels that might make stuff slower 😉☆64Updated this week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆134Updated last week
- ☆147Updated 10 months ago
- A Quirky Assortment of CuTe Kernels☆653Updated 2 weeks ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆385Updated this week
- TPU inference for vLLM, with unified JAX and PyTorch support.☆161Updated this week
- ☆113Updated last year
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆111Updated this week
- Github mirror of trition-lang/triton repo.☆98Updated this week
- ☆125Updated 3 weeks ago
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆244Updated 6 months ago