Starred repositories
A generative speech model for daily dialogue.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative)
An Open Source implementation of Notebook LM with more flexibility and features
A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines.
A privacy-first distributed training framework built on MLX for Apple Silicon, enabling secure and efficient AI model training across multiple devices while preserving data privacy.
slime is an LLM post-training framework for RL Scaling.
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
SGLang is a fast serving framework for large language models and vision language models.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Interact with your documents using the power of GPT, 100% privately, no data leaks
Large Language Model Text Generation Inference
Andrej Karpathy's micrograd library implemented in Go
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Official PyTorch implementation for "Large Language Diffusion Models"
A lightweight design for computation-communication overlap.
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
My learning notes/codes for ML SYS.
Supercharge Your LLM with the Fastest KV Cache Layer
CUDA Python: Performance meets Productivity