Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
☆2,184Apr 9, 2026Updated last week
Alternatives and similar repositories for mirage
Users that are interested in mirage are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Tile primitives for speedy kernels☆3,312Apr 8, 2026Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,403Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,372Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,478Apr 10, 2026Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,286Aug 28, 2025Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A Easy-to-understand TensorOp Matmul Tutorial☆423Mar 5, 2026Updated last month
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆759Aug 6, 2025Updated 8 months ago
- A throughput-oriented high-performance serving framework for LLMs☆952Mar 29, 2026Updated 2 weeks ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,564Apr 9, 2026Updated last week
- Development repository for the Triton language and compiler☆18,902Updated this week
- Kernels, of the mega variety :)☆705Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,051Sep 4, 2024Updated last year
- 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
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆106Jun 28, 2025Updated 9 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- FlagGems is an operator library for large language models implemented in the Triton Language.☆953Updated this week
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.☆800Oct 13, 2025Updated 6 months ago
- 🚀 Efficient implementations for emerging model architectures☆4,878Updated this week
- Fast low-bit matmul kernels in Triton☆443Apr 4, 2026Updated last week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,872Apr 9, 2026Updated last week
- Efficient Triton Kernels for LLM Training☆6,279Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆474May 30, 2025Updated 10 months ago
- Puzzles for learning Triton☆2,374Apr 1, 2026Updated 2 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,071Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,319Mar 22, 2026Updated 3 weeks ago
- A Quirky Assortment of CuTe Kernels☆924Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆931Mar 24, 2026Updated 3 weeks ago
- A list of awesome compiler projects and papers for tensor computation and deep learning.☆2,734Oct 19, 2024Updated last year
- SGLang is a high-performance serving framework for large language models and multimodal models.☆25,643Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,152May 8, 2024Updated last year
- Shared Middle-Layer for Triton Compilation☆330Dec 5, 2025Updated 4 months ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆57May 29, 2024Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆471Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A list of tutorials, paper, talks, and open-source projects for emerging compiler and architecture☆523Jan 15, 2025Updated last year
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆600Aug 12, 2025Updated 8 months ago
- Fast and memory-efficient exact attention☆23,344Updated this week
- ☆261Jul 11, 2024Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆826Mar 6, 2025Updated last year
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆835Updated this week
- Perplexity GPU Kernels☆565Nov 7, 2025Updated 5 months ago