Run PyTorch LLMs locally on servers, desktop and mobile
☆3,615Sep 10, 2025Updated last year
Alternatives and similar repositories for torchchat
Users that are interested in torchchat are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A PyTorch native platform for training generative AI models☆5,855Updated this week
- PyTorch native post-training library☆5,824Sep 9, 2026Updated last month
- On-device AI across mobile, embedded and edge for PyTorch☆5,128Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆13,732Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,265Aug 22, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official inference repo for FLUX.1 models☆26,041Jul 31, 2025Updated last year
- Efficient Triton Kernels for LLM Training☆6,675Updated this week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆18,579May 19, 2026Updated 5 months ago
- A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.☆3,955Oct 20, 2026Updated last week
- PyTorch native quantization for training and inference☆3,016Updated this week
- Open GenAI Stack☆8,444Updated this week
- Universal LLM Deployment Engine with ML Compilation☆23,281Updated this week
- Agentic components of the Llama Stack APIs☆4,286Aug 5, 2025Updated last year
- An open-source RAG-based tool for chatting with your documents.☆25,831Jul 14, 2026Updated 3 months ago
- 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.
- LLM training in simple, raw C/CUDA☆31,261Jun 26, 2025Updated last year
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.☆78,568Updated this week
- lightweight, standalone C++ inference engine for Google's Gemma models.☆7,067Updated this week
- Distribute and run LLMs with a single file.☆26,491Oct 12, 2026Updated 2 weeks ago
- See, hear, and interact on your local devices.☆26,981Updated this week
- A lightweight library for portable low-level GPU computation using WebGPU.☆3,993Aug 21, 2026Updated 2 months ago
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.☆22,080Apr 15, 2026Updated 6 months ago
- Fast, flexible LLM inference☆7,780Updated this week
- CoreNet: A library for training deep neural networks☆7,010Sep 25, 2026Updated last month
- 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 high-throughput and memory-efficient inference and serving engine for LLMs☆95,520Updated this week
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆11,314Sep 9, 2026Updated last month
- An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.☆31,691Sep 30, 2025Updated last year
- Large Language Model Text Generation Inference☆10,882Mar 21, 2026Updated 7 months ago
- Go ahead and axolotl questions☆12,632Updated this week
- DSPy: The framework for programming—not prompting—language models☆38,818Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,771Jul 18, 2025Updated last year
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,230Updated this week
- ☆3,091Jun 16, 2026Updated 4 months ago
- 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.
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆36,463Updated this week
- MLX: An array framework for Apple silicon☆28,944Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,848Jul 1, 2024Updated 2 years ago
- The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build cu…☆10,753Updated this week
- LlamaIndex is the document processing platform for AI☆52,691Updated this week
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆979Nov 16, 2025Updated 11 months ago
- llama3 implementation one matrix multiplication at a time☆15,202May 23, 2024Updated 2 years ago