Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
☆2,560Oct 17, 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☆1,569Sep 18, 2026Updated 3 weeks ago
- Tile primitives for speedy kernels☆3,755Sep 12, 2026Updated last month
- Kernels, of the mega variety :)☆849May 26, 2026Updated 4 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,672Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,638Updated this week
- 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.
- A Quirky Assortment of CuTe Kernels☆1,176Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,374Aug 28, 2025Updated last year
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆965Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,613Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,866Sep 24, 2026Updated 3 weeks ago
- Accelerating MoE with IO and Tile-aware Optimizations☆780Aug 29, 2026Updated last month
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆496Sep 17, 2026Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆976Mar 29, 2026Updated 6 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆771Aug 6, 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.
- Perplexity GPU Kernels☆612Nov 7, 2025Updated 11 months ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆1,293Mar 24, 2026Updated 6 months ago
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆8,978Updated this week
- Building the Virtuous Cycle for AI-driven LLM Systems☆295Sep 25, 2026Updated 3 weeks ago
- Development repository for the Triton language and compiler☆20,393Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,939Updated this week
- A lightweight design for computation-communication overlap.☆249Jan 20, 2026Updated 8 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,164Sep 4, 2024Updated 2 years ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,821Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- mKernel: fast multi-node, multi-GPU fused kernels☆297Updated this week
- Open ABI and FFI for Machine Learning Systems☆471Updated this week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆1,151Updated this week
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,157Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆454Mar 5, 2026Updated 7 months ago
- Efficient Triton Kernels for LLM Training☆6,663Updated this week
- Puzzles for learning Triton☆2,641Apr 1, 2026Updated 6 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆564Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,900Oct 11, 2026Updated last week
- 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.
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,544Updated this week
- Github mirror of trition-lang/triton repo.☆201Updated this week
- Fast low-bit matmul kernels in Triton☆488Oct 1, 2026Updated 2 weeks 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…☆3,585Updated this week
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,086Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,313Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆525Aug 24, 2026Updated last month