🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

Warp is an agentic development environment, born out of the terminal.

Mouse Jiggler is a very simple piece of software whose sole function is to "fake" mouse input to Windows, and jiggle the mouse pointer back and forth.

xoul agent client

vLLM plugin for RBLN NPU

Self-supervised Pre-training of ECG Classifiers with Joint-Embedding Predictive Architecture

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. This fork is used to manage Swift’s stable releases of Clang as well as support the Swift project.

A repository containing links to accepted proposals for GSoC, Hopefully this helps someone write a better proposal and get accepted into the program

An open-source AI agent that brings the power of Gemini directly into your terminal.

Hosts MLSys Competition Track Problems

🤖 Places where you can learn robotics (and stuff like that) online 🤖

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

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

Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"

Gateway API Inference Extension

Achieve state of the art inference performance with modern accelerators on Kubernetes

LLMPerf is a library for validating and benchmarking LLMs

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

A framework for efficient model inference with omni-modality models

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

Minimal yet performant LLM examples in pure JAX