shimmyshimmer
Follow
Stars
On-device AI across mobile, embedded and edge for PyTorch
SGLang is a fast serving framework for large language models and vision language models.
🛜 100+ offline-first networking tools and utilities
🌐 The all-in-one tool, for keeping track of your domain name portfolio. Got domain names? Get Domain Locker!
✨ An advanced 3D Gaussian Splatting renderer for THREE.js
The HTML5 Creation Engine: Create beautiful digital content with the fastest, most flexible 2D WebGL renderer.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
dstack is an open-source control plane for running development, training, and inference jobs on GPUs—across hyperscalers, neoclouds, or on-prem.
Brevitas: neural network quantization in PyTorch
An interface library for RL post training with environments.
Storyboarding tool to help creatives go from idea to video in minutes. Visually build, connect, and run creative asset pipelines for generative media. Create production-grade short form content, cr…
Agent Interface Discovery
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
PyTorch native quantization and sparsity for training and inference
Curate High Quality Datasets, Train, Evaluate and Ship! 🚀
Unsloth fine-tuning resources.
this is a dungeon ai run locally that use your llm
Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.
🌐 The open-source Agentic browser; privacy-first alternative to ChatGPT Atlas, Perplexity Comet, Dia.
An implementation of GRPO for Unsloth's VLMs training
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.
Supercharge Your LLM with the Fastest KV Cache Layer