Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

🤗 smolagents: a barebones library for agents that think in python code.

This repository contains the Hugging Face Agents Course.

interview-coder-withoupaywall-opensource

A simple, performant and scalable Jax LLM!

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

No fortress, purely open ground. OpenManus is Coming.

summary of each chapter & example code from the book

🎓 Path to a free self-taught education in Computer Science!

Train transformer language models with reinforcement learning.

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

A curated list of awesome high performance computing resources

s1: Simple test-time scaling

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

DeepEP: an efficient expert-parallel communication library

A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.

FlashMLA: Efficient MLA decoding kernels

Expert Parallelism Load Balancer

Ongoing research training transformer models at scale

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

SGLang is a fast serving framework for large language models and vision language models.

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

An ML Systems Onboarding list

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.