Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…

contaiNERD CTL - Docker-compatible CLI for containerd, with support for Compose, Rootless, eStargz, OCIcrypt, IPFS, ...

A high-throughput and memory-efficient inference and serving engine for LLMs

SGLang is a high-performance serving framework for large language models and multimodal models.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Scripts to modify waydroid

Static suckless single batch CUDA-only qwen3-0.6B mini inference engine

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Advanced Text Editor for Android

Android Music Player

neovim frontend for opencode - a terminal-based AI coding agent

Notes About How To Accelerate ML Systems

Fast typo-resistant fuzzy matching via SIMD smith waterman, similar algorithm to FZF/FZY

Performant, modular picker plugin for Neovim

Performant, batteries-included completion plugin for Neovim

A tool-use-focused LLM plugin for neovim.

A keyboard-driven, vim-like browser based on Python and Qt.

pprof is a tool for visualization and analysis of profiling data

Vim's quickfix errorformat implementation in Go

Learn books from Docker & K8s

Remove continuation characters when joining lines in vim

Minimal Eye-candy keys screencaster for Neovim 200 ~ LOC

Run your tests at the speed of thought

macOS: mount any linux-supported filesystem read/write using NFS and a microVM

Aider's VSCode extension, seamlessly integrated into VSCode

Bundle of more than 30 new text objects for Neovim.

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

High-performance In-browser LLM Inference Engine