NVIDIA / jaxppLinks
JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training
☆55Updated 2 weeks ago
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☆90Updated 6 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆264Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆491Updated this week
- ☆93Updated 11 months ago
- ☆242Updated this week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 4 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆125Updated 5 months ago
- TritonParse: A Compiler Tracer, Visualizer, and Reproducer for Triton Kernels☆164Updated this week
- Applied AI experiments and examples for PyTorch☆299Updated 2 months ago
- Github mirror of trition-lang/triton repo.☆92Updated this week
- How to ensure correctness and ship LLM generated kernels in PyTorch☆107Updated last week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆120Updated this week
- This repository contains the experimental PyTorch native float8 training UX☆223Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆215Updated this week
- ☆241Updated last year
- ☆141Updated 10 months ago
- Fast low-bit matmul kernels in Triton☆385Updated last week
- Framework to reduce autotune overhead to zero for well known deployments.☆84Updated last month
- Collection of kernels written in Triton language☆157Updated 6 months ago
- ring-attention experiments☆155Updated last year
- Ahead of Time (AOT) Triton Math Library☆80Updated last week
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- Cataloging released Triton kernels.☆263Updated last month
- ☆112Updated last year
- a size profiler for cuda binary☆51Updated 3 weeks ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆358Updated last week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆117Updated last year
- A Quirky Assortment of CuTe Kernels☆637Updated 2 weeks ago
- ☆178Updated last year
- ☆123Updated last week