Kernels, of the mega variety :)
☆693Mar 23, 2026Updated this week
Alternatives and similar repositories for Megakernels
Users that are interested in Megakernels are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Distributed Compiler based on Triton for Parallel Systems☆1,394Mar 11, 2026Updated last week
- ☆65Apr 26, 2025Updated 10 months ago
- Tile primitives for speedy kernels☆3,244Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,159Updated this week
- ☆183May 7, 2025Updated 10 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,194Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,273Aug 28, 2025Updated 6 months ago
- A Quirky Assortment of CuTe Kernels☆863Updated this week
- Perplexity GPU Kernels☆564Nov 7, 2025Updated 4 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,403Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆466May 30, 2025Updated 9 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆49Jan 21, 2026Updated 2 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆253Feb 13, 2026Updated last month
- ☆52May 19, 2025Updated 10 months ago
- High-performance LLM operator library built on TileLang.☆93Updated this week
- A lightweight design for computation-communication overlap.☆225Jan 20, 2026Updated 2 months ago
- ☆261Jul 11, 2024Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,041Sep 4, 2024Updated last year
- ☆37Jul 19, 2025Updated 8 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆210Updated this week
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆456Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆409Mar 5, 2026Updated 2 weeks ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆19Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆949Oct 29, 2025Updated 4 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆336Jul 2, 2024Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Jul 4, 2025Updated 8 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆821Mar 6, 2025Updated last year
- ☆38Aug 7, 2025Updated 7 months ago
- Puzzles for learning Triton☆2,336Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆332Updated this week
- Fastest kernels written from scratch☆561Sep 18, 2025Updated 6 months ago
- [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization☆22Feb 5, 2026Updated last month
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆961Feb 25, 2026Updated 3 weeks ago
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆809Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆531Feb 10, 2025Updated last year
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,484Updated this week
- Helpful tools and examples for working with flex-attention☆1,161Feb 8, 2026Updated last month
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆193Jan 28, 2025Updated last year
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆752Aug 6, 2025Updated 7 months ago