On-device AI across mobile, embedded and edge for PyTorch
☆4,809Jul 18, 2026Updated this week
Alternatives and similar repositories for executorch
Users that are interested in executorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,617Sep 10, 2025Updated 10 months ago
- PyTorch native quantization and sparsity for training and inference☆2,906Updated this week
- 🤗 Optimum ExecuTorch☆132May 26, 2026Updated last month
- Support PyTorch model conversion with LiteRT.☆1,066Updated this week
- PyTorch native post-training library☆5,783Updated this week
- 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.
- Universal LLM Deployment Engine with ML Compilation☆22,966Updated this week
- Tensor library for machine learning☆15,007Updated this week
- LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via e…☆3,125Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,148Updated this week
- Development repository for the Triton language and compiler☆19,717Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆86,566Updated this week
- MLX: An array framework for Apple silicon☆27,594Updated this week
- A PyTorch native platform for training generative AI models☆5,538Updated this week
- LLM inference in C/C++☆120,870Updated this week
- 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.
- ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator☆21,124Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,487Updated this week
- Distribute and run LLMs with a single file.☆25,369Updated this week
- Inference Llama 2 in one file of pure C☆19,740Aug 6, 2024Updated last year
- Fast and memory-efficient exact attention☆24,483Updated this week
- Fast, flexible LLM inference☆7,493Updated this week
- Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) an…☆1,166Updated this week
- lightweight, standalone C++ inference engine for Google's Gemma models.☆6,985Updated this week
- High-speed Large Language Model Serving for Local Deployment☆9,643May 11, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Accessible large language models via k-bit quantization for PyTorch.☆8,330Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,977Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,725Updated this week
- Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.☆68,371Updated this week
- Open GenAI Stack☆8,422Updated this week
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,663Updated this week
- LLM training in simple, raw C/CUDA☆30,570Jun 26, 2025Updated last year
- CoreNet: A library for training deep neural networks☆7,001Oct 9, 2025Updated 9 months ago
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆4,404Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆13,488Jul 6, 2026Updated last week
- Generative AI extensions for onnxruntime☆1,086Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,682Updated this week
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆447Updated this week
- Open Machine Learning Compiler Framework☆13,582Updated this week
- Minimalist ML framework for Rust☆20,688Updated this week
- Fast Multimodal LLM on Mobile Devices☆1,570Jun 26, 2026Updated 3 weeks ago