Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
☆2,602Nov 6, 2026Updated this 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:
- Distributed Compiler and Optimized Parallel Kernels☆1,577Sep 18, 2026Updated last month
- Tile primitives for speedy kernels☆3,795Sep 12, 2026Updated last month
- Kernels, of the mega variety :)☆876May 26, 2026Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,866Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,920Updated 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 Quirky Assortment of CuTe Kernels☆1,189Oct 30, 2026Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,376Aug 28, 2025Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,887Sep 24, 2026Updated last month
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆978Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,703Updated this week
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆499Oct 23, 2026Updated 2 weeks ago
- Accelerating MoE with IO and Tile-aware Optimizations☆787Aug 29, 2026Updated 2 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆772Aug 6, 2025Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆976Mar 29, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- mKernel: fast multi-node, multi-GPU fused kernels☆308Oct 17, 2026Updated 2 weeks ago
- Development repository for the Triton language and compiler☆20,529Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆1,318Mar 24, 2026Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,174Sep 4, 2024Updated 2 years ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆305Sep 25, 2026Updated last month
- 🚀 Efficient implementations for emerging model architectures☆6,025Updated this week
- Efficient Triton Kernels for LLM Training☆6,686Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆9,162Oct 20, 2026Updated 2 weeks ago
- Perplexity GPU Kernels☆614Nov 7, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A Easy-to-understand TensorOp Matmul Tutorial☆459Mar 5, 2026Updated 8 months ago
- A lightweight design for computation-communication overlap.☆252Jan 20, 2026Updated 9 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,994Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆1,169Updated this week
- Open ABI and FFI for Machine Learning Systems☆476Updated this week
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,167Updated this week
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,541Oct 19, 2026Updated 2 weeks ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,903Updated this week
- Fast low-bit matmul kernels in Triton☆491Oct 1, 2026Updated last month
- 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.
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,156Updated this week
- Puzzles for learning Triton☆2,662Apr 1, 2026Updated 7 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,601Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆570Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆526Aug 24, 2026Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆867Mar 6, 2025Updated last year
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,575Updated this week