High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.
☆45Jul 22, 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:
- Distillation pipeline from pretrained Transformers to customized FLA models☆13Aug 4, 2025Updated last year
- IMMA-based **FP8-as-storage** GEMM experiments for Ampere (sm_86 / RTX 3090 Ti).☆28Jan 30, 2026Updated 9 months ago
- Optimize GEMM with tensorcore step by step☆40Dec 17, 2023Updated 2 years ago
- Optimize SGEMM step by step☆10Sep 4, 2024Updated 2 years ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆71Jul 30, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆20Updated this week
- Grouped Query Experts☆12Sep 21, 2026Updated last month
- ☆12May 8, 2026Updated 6 months ago
- CUDA Craftax-Classic: 7x faster RL training than JAX☆80Sep 10, 2026Updated 2 months ago
- Region-level profiling for CUDA kernels with trace, NVBit, CUPTI, NSys, and an interactive Explorer.☆135Apr 17, 2026Updated 7 months ago
- a rubric driven prioritized replay rl algo to maximise continual learning☆16Oct 12, 2025Updated last year
- Cataloging released Triton kernels.☆315Sep 9, 2025Updated last year
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 4 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆315Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- The Newton-Muon optimizer☆35Jun 5, 2026Updated 5 months ago
- some mixture of experts architecture implementations☆28Mar 22, 2024Updated 2 years ago
- Implementation of Fast Weight Attention☆35Sep 17, 2026Updated 2 months ago
- Github mirror of trition-lang/triton repo.☆207Updated this week
- A CUDA kernel optimization toolkit for validation, benchmarking, Nsight Compute profiling, bottleneck analysis, and iterative tuning. It …☆218Sep 5, 2026Updated 2 months ago
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆319Sep 12, 2026Updated 2 months ago
- NCCL communication API layer, and transport layer created from first principles.☆16Aug 20, 2025Updated last year
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated last year
- Step-by-step GEMM optimization, one hardware feature at a time. High performance CuTeDSL kernels for H100, B200 and RTX 50s GPUs. This re…☆23May 14, 2026Updated 6 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.
- ☆56Oct 22, 2026Updated 3 weeks ago
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated last year
- Kernels by MakoraGenerate☆15May 26, 2026Updated 5 months ago
- Reclaim disk space from build artifacts. Rust TUI for cleaning target/, node_modules/, bin/, and obj/ across your workspace.☆16Aug 2, 2026Updated 3 months ago
- Implemented and benchmarked KV cache compression methods for LLM inference in Triton. Optimized kernels for KIVI and TurboQuant with Flas…☆18Jun 19, 2026Updated 4 months ago
- Simple proof of concept application that lets us upload shader blobs and run them on the mali kernel drivers for Android☆17Mar 12, 2018Updated 8 years ago
- GPU Functional Descriptor for memory access☆36May 24, 2026Updated 5 months ago
- A Python interface for the Dawn WebGPU engine☆24Jan 10, 2026Updated 10 months ago
- A inference framework that adapt to diverse and dynamic agent workload☆118Updated this week
- 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.
- Reverse engineered the Apple Neural Engine, with working Python and Objective C samples☆41Feb 1, 2026Updated 9 months ago
- Research slot☆14Apr 16, 2026Updated 7 months ago
- Row-wise block scaling for fp8 quantization matrix multiplication. Solution to GPU mode AMD challenge.☆19Feb 9, 2026Updated 9 months ago
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆43Oct 24, 2026Updated 3 weeks ago
- ☆279Jan 2, 2025Updated last year
- ☆49Nov 1, 2025Updated last year
- Aggressive decode optimizations for Qwen3-0.6B on RTX 5090☆64Feb 25, 2026Updated 8 months ago
Are these results useful?