High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.
☆43Jul 22, 2026Updated last month
Alternatives and similar repositories for triton-kernels
Users that are interested in triton-kernels are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆39Jul 9, 2026Updated 2 months ago
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆25Jan 30, 2026Updated 7 months ago
- Optimize GEMM with tensorcore step by step☆40Dec 17, 2023Updated 2 years ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆69Jul 30, 2026Updated last month
- The Newton-Muon optimizer☆32Jun 5, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Github mirror of trition-lang/triton repo.☆196Updated this week
- Implementation of Fast Weight Attention☆35Aug 20, 2026Updated 3 weeks ago
- NCCL communication API layer, and transport layer created from first principles.☆16Aug 20, 2025Updated last year
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated last year
- GPU Functional Descriptor for memory access☆34May 24, 2026Updated 3 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆276Updated this week
- ☆18Apr 10, 2026Updated 5 months ago
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated last year
- A framework for in context learning for code optimization☆61Mar 14, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Aggressive decode optimizations for Qwen3-0.6B on RTX 5090☆63Feb 25, 2026Updated 6 months ago
- A CUDA kernel optimization toolkit for validation, benchmarking, Nsight Compute profiling, bottleneck analysis, and iterative tuning. It …☆206Sep 5, 2026Updated 2 weeks ago
- Cataloging released Triton kernels.☆311Sep 9, 2025Updated last year
- ☆45Nov 1, 2025Updated 10 months ago
- ☆12Mar 16, 2022Updated 4 years ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆89May 29, 2026Updated 3 months ago
- ☆25Feb 27, 2026Updated 6 months ago
- High-performance LLM operator library built on TileLang.☆188Updated this week
- PyTorch Code for the Paper: "Exploiting Uncertainty of Loss Landscape for Stochastic Optimization [Bhaskara et al. (2019)]☆16Apr 30, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆306Sep 12, 2026Updated last week
- ☆48Dec 13, 2025Updated 9 months ago
- Optimizing scheduler. Combinatorial instruction scheduling project.☆29Jun 8, 2026Updated 3 months ago
- ☆16May 14, 2025Updated last year
- Repository for the CUDA H100 Course☆76Apr 12, 2026Updated 5 months ago
- ☆19Mar 29, 2026Updated 5 months ago
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 6 months ago
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆138Feb 10, 2026Updated 7 months ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆14Aug 28, 2019Updated 7 years ago
- ☆135Mar 19, 2026Updated 6 months ago
- Exercises for Learning MLIR (Originally written for PPoPP 2026)☆109Jul 21, 2026Updated last month
- high-performance linear attention kernel library built on TileLang☆704Updated this week
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆28Mar 22, 2026Updated 5 months ago
- DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transi…☆17Oct 13, 2025Updated 11 months ago
- Code and data to explore neural scaling laws of xLSTM and Transformer models.☆24Apr 8, 2026Updated 5 months ago