Lists (1)
Stars
Minimal yet performant LLM examples in pure JAX
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
AGENTS.md β a simple, open format for guiding coding agents
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
SGLang is a fast serving framework for large language models and vision language models.
γC++ 17 The Complete Guideγ- ηΏ»θ―δΈ
π₯ Fast State-of-the-Art Tokenizers optimized for Research and Production
Cross-platform, customizable ML solutions for live and streaming media.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A python library for converting Pytorch modules into a circle model that is a lightweight and efficient representation in ONE designed for optimized on-device neural network inference.
Hackable and optimized Transformers building blocks, supporting a composable construction.
Dynamic Memory Management for Serving LLMs without PagedAttention
The simplest, fastest repository for training/finetuning medium-sized GPTs.
An unnecessarily tiny implementation of GPT-2 in NumPy.
Simple implementation of Speculative Sampling in NumPy for GPT-2.
γγΌγγγδ½γ Deep Learning βΊγ(O'Reilly Japan, 2024)
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
A basic PyTorch implementation of 'Denoising Diffusion Probabilistic Models'
Fine-tuning & Reinforcement Learning for LLMs. π¦₯ Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
A flexible distributed key-value database that is optimized for caching and other realtime workloads.