Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
☆2,148Feb 23, 2026Updated last week
Alternatives and similar repositories for mirage
Users that are interested in mirage are comparing it to the libraries listed below
Sorting:
- Tile primitives for speedy kernels☆3,202Feb 24, 2026Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,371Feb 13, 2026Updated 3 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆5,057Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,284Feb 28, 2026Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,264Aug 28, 2025Updated 6 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆753Aug 6, 2025Updated 7 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆409Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,025Sep 4, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆947Oct 29, 2025Updated 4 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆909Updated this week
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆194Jan 28, 2025Updated last year
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,348Updated this week
- Development repository for the Triton language and compiler☆18,501Updated this week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆106Jun 28, 2025Updated 8 months ago
- kernels, of the mega variety☆684Updated this week
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆794Oct 13, 2025Updated 4 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,474Updated this week
- Fast low-bit matmul kernels in Triton☆436Feb 1, 2026Updated last month
- Efficient Triton Kernels for LLM Training☆6,189Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆595Aug 12, 2025Updated 6 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,863Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆464May 30, 2025Updated 9 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,206Feb 27, 2026Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,843Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆836Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,144May 8, 2024Updated last year
- Puzzles for learning Triton☆2,324Nov 18, 2024Updated last year
- A list of awesome compiler projects and papers for tensor computation and deep learning.☆2,733Oct 19, 2024Updated last year
- Shared Middle-Layer for Triton Compilation☆329Dec 5, 2025Updated 3 months ago
- A Quirky Assortment of CuTe Kernels☆838Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,905Updated this week
- A PyTorch native platform for training generative AI models☆5,098Feb 28, 2026Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆817Mar 6, 2025Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆446Feb 4, 2026Updated last month
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆774Updated this week
- A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.☆1,005Sep 19, 2024Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,707Updated this week
- ☆262Jul 11, 2024Updated last year
- CUDA Kernel Benchmarking Library☆827Feb 28, 2026Updated last week