High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.
☆31Apr 5, 2026Updated 3 months ago
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:
- A framework for in context learning for code optimization☆58Mar 14, 2026Updated 4 months ago
- Optimize GEMM with tensorcore step by step☆40Dec 17, 2023Updated 2 years ago
- some mixture of experts architecture implementations☆27Mar 22, 2024Updated 2 years ago
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆24Updated this week
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 5 months ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆63Jul 7, 2026Updated last week
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆115Feb 10, 2026Updated 5 months ago
- General Matrix Multiplication using NVIDIA Tensor Cores☆28Jan 25, 2025Updated last year
- The Newton-Muon optimizer☆30Jun 5, 2026Updated last month
- GPU Functional Descriptor for memory access☆34May 24, 2026Updated last month
- Implementation of Fast Weight Attention☆32Jun 3, 2026Updated last month
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated 10 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆251Jun 21, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A CUDA kernel optimization toolkit for validation, benchmarking, Nsight Compute profiling, bottleneck analysis, and iterative tuning. It …☆190Apr 22, 2026Updated 2 months ago
- ☆32Jul 2, 2025Updated last year
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆84May 29, 2026Updated last month
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆148Jun 10, 2026Updated last month
- ☆12Mar 16, 2022Updated 4 years ago
- ☆28Updated this week
- Crosshair guidelines for ComfyUI to help align nodes and groups while moving or resizing.☆38Apr 28, 2026Updated 2 months ago
- Flash Attention in 300-500 lines of CUDA/C++☆39Aug 22, 2025Updated 10 months ago
- PyTorch Code for the Paper: "Exploiting Uncertainty of Loss Landscape for Stochastic Optimization [Bhaskara et al. (2019)]☆16Apr 30, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Triton Compiler related materials.☆44Mar 16, 2026Updated 3 months ago
- Repository for the CUDA H100 Course☆66Apr 12, 2026Updated 3 months ago
- Optimizing scheduler. Combinatorial instruction scheduling project.☆28Jun 8, 2026Updated last month
- ☆16May 14, 2025Updated last year
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated last year
- This is the official implementation for paper "On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond".☆23Nov 17, 2025Updated 7 months ago
- ☆34Jan 9, 2026Updated 6 months ago
- ☆134Mar 19, 2026Updated 3 months ago
- ☆14Aug 28, 2019Updated 6 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations☆91Jan 12, 2026Updated 6 months ago
- [ICLRW'26] EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation☆49Apr 21, 2026Updated 2 months ago
- ☆45Nov 1, 2025Updated 8 months ago
- Official Project Page for HLA: Higher-order Linear Attention (https://arxiv.org/abs/2510.27258)☆102Jun 15, 2026Updated 3 weeks ago
- [CVPR 2026] Official repo for "EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation"☆60Mar 13, 2026Updated 4 months ago
- high-performance linear attention kernel library built on TileLang☆590Updated this week
- A fully functional Convolutional VAE implemented in pure C from scratch.☆24Jan 19, 2026Updated 5 months ago