Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!
☆208Feb 18, 2026Updated last week
Alternatives and similar repositories for reference-kernels
Users that are interested in reference-kernels are comparing it to the libraries listed below
Sorting:
- ☆96Feb 18, 2026Updated last week
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Aug 9, 2025Updated 6 months ago
- Write a fast kernel and run it on Discord. See how you compare against the best!☆74Feb 18, 2026Updated last week
- Personal solutions to the Triton Puzzles☆20Jul 18, 2024Updated last year
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆20Jan 24, 2025Updated last year
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆820Updated this week
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆106Sep 24, 2025Updated 5 months ago
- Step by step implementation of a fast softmax kernel in CUDA☆61Jan 6, 2025Updated last year
- Attention in SRAM on Tenstorrent Grayskull☆40Jul 18, 2024Updated last year
- GPU programming related news and material links☆1,997Sep 17, 2025Updated 5 months ago
- Quantized LLM training in pure CUDA/C++.☆241Updated this week
- A curated list of resources for learning and exploring Triton, OpenAI's programming language for writing efficient GPU code.☆459Mar 10, 2025Updated 11 months ago
- Cataloging released Triton kernels.☆295Sep 9, 2025Updated 5 months ago
- MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI tr…☆52Updated this week
- ☆18Jun 6, 2025Updated 8 months ago
- ☆23Jul 11, 2025Updated 7 months ago
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2025☆31Oct 22, 2025Updated 4 months ago
- CargoCoin is designed to be a smart contract, crypto currency platform, decentralising global trade and transport. The platform target is…☆13Aug 8, 2018Updated 7 years ago
- Fast CUDA matrix multiplication from scratch☆1,060Sep 2, 2025Updated 5 months ago
- It is an LLM-based AI agent, which can write correct and efficient gpu kernels automatically.☆68Updated this week
- An MLIR-based compiler that takes GPU kernels and compiles them to real hardware instructions. Interactive web visualizer included.☆49Updated this week
- Fastest kernels written from scratch☆548Sep 18, 2025Updated 5 months ago
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆172Feb 21, 2026Updated last week
- ☆18Dec 2, 2024Updated last year
- AI Tensor Engine for ROCm☆356Feb 21, 2026Updated last week
- ☆30Jan 9, 2026Updated last month
- Triton backend for managing the model state tensors automatically in sequence batcher☆17Feb 12, 2024Updated 2 years ago
- Wave: Python Domain-Specific Language for High Performance Machine Learning☆45Updated this week
- Ship correct and fast LLM kernels to PyTorch☆142Jan 14, 2026Updated last month
- Super fast FP32 matrix multiplication on RDNA3☆84Mar 30, 2025Updated 11 months ago
- Material for gpu-mode lectures☆5,773Feb 1, 2026Updated 3 weeks ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆147May 10, 2025Updated 9 months ago
- ☆52Dec 10, 2025Updated 2 months ago
- Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Lar…☆103Jan 8, 2026Updated last month
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated 8 months ago
- Fast and Furious AMD Kernels☆368Feb 15, 2026Updated last week
- Tile primitives for speedy kernels☆3,183Updated this week
- General Matrix Multiplication using NVIDIA Tensor Cores☆28Jan 25, 2025Updated last year
- Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X☆75Feb 11, 2026Updated 2 weeks ago