An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682
☆138Jun 29, 2026Updated 2 months ago
Alternatives and similar repositories for AutoMegaKernel
Users that are interested in AutoMegaKernel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High-performance GPU kernels written in TIRx.☆98Updated this week
- ☆103Updated this week
- Skills for writing tilelang and debugging with CUDA toolkits.☆137May 20, 2026Updated 3 months ago
- High-performance LLM operator library built on TileLang.☆181Updated this week
- ☆32Jul 2, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- mKernel: fast multi-node, multi-GPU fused kernels☆270Updated this week
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆17Aug 6, 2026Updated last month
- Tile-based language built for AI computation across all scales☆190Aug 25, 2026Updated 2 weeks ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆41Updated this week
- ☆446Aug 26, 2026Updated 2 weeks ago
- ☆37Aug 7, 2025Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆200Feb 11, 2026Updated 7 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200☆123Feb 28, 2026Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆77Aug 8, 2026Updated last month
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆21Aug 28, 2026Updated 2 weeks ago
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,555Mar 19, 2026Updated 5 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆118Aug 4, 2026Updated last month
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆159Updated this week
- ☆225Aug 26, 2026Updated 2 weeks ago
- ☆51Aug 17, 2026Updated 3 weeks ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated last month
- ☆54May 19, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆26Jun 10, 2026Updated 3 months ago
- Agent-friendly GPU profile-query CLI☆120Aug 21, 2026Updated 3 weeks ago
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆36May 22, 2026Updated 3 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆105Apr 7, 2026Updated 5 months ago
- Kernels, of the mega variety :)☆822May 26, 2026Updated 3 months ago
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆229Updated this week
- My tests and experiments with some popular dl frameworks.☆17Sep 11, 2025Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,490Updated this week
- ☆46Oct 15, 2025Updated 10 months 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 simple API to use CUPTI☆10Aug 19, 2025Updated last year
- A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch☆382Jul 9, 2026Updated 2 months ago
- ☆21Mar 17, 2026Updated 5 months ago
- ☆51Jul 27, 2026Updated last month
- Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extensio…☆25May 5, 2026Updated 4 months ago
- Github mirror of trition-lang/triton repo.☆195Updated this week
- An Optimizer for Nvidia Compilers.☆134Aug 28, 2026Updated 2 weeks ago