meta-pytorch / tritonbenchLinks
Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
☆202Updated this week
Alternatives and similar repositories for tritonbench
Users that are interested in tritonbench are comparing it to the libraries listed below
Sorting:
- Applied AI experiments and examples for PyTorch☆289Updated 2 months ago
- ☆85Updated 9 months ago
- Cataloging released Triton kernels.☆251Updated 7 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆108Updated 2 months ago
- A Quirky Assortment of CuTe Kernels☆388Updated last week
- ☆227Updated last week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆212Updated this week
- ☆228Updated last year
- Collection of kernels written in Triton language☆144Updated 4 months ago
- extensible collectives library in triton☆88Updated 4 months ago
- Fast low-bit matmul kernels in Triton☆339Updated last week
- A collection of memory efficient attention operators implemented in the Triton language.☆276Updated last year
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆260Updated 3 weeks ago
- kernels, of the mega variety☆471Updated 2 months ago
- ☆106Updated 7 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- ☆108Updated 11 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆207Updated this week
- ☆96Updated 11 months ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆215Updated last year
- Fastest kernels written from scratch☆311Updated 4 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆93Updated last month
- A lightweight design for computation-communication overlap.☆155Updated last month
- ☆80Updated 6 months ago
- ring-attention experiments☆147Updated 9 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆79Updated 2 weeks ago
- ☆60Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆134Updated 3 weeks ago