- Beijing, PRC
Stars
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.
FlashInfer: Kernel Library for LLM Serving
🧠「大模型」2小时完全从0训练64M的小参数LLM!Train a 64M-parameter LLM from scratch in just 2h!
[ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.
A ~9M parameter LLM that talks like a small fish.
Development repository for the Triton language and compiler
Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more
The paper list of "Memory in the Age of AI Agents: A Survey"
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
A terminal workspace with batteries included
Experimental self-improving multi-agent coding system: a root agent recursively decomposes goals and delegates to specialist subagents, learning from failures by mutating a git-backed agent genome.…
An agentic skills framework & software development methodology that works.
Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.
SGLang is a high-performance serving framework for large language models and multimodal models.
HY-Motion model for 3D human motion or 3D character animation generation.
Wan: Open and Advanced Large-Scale Video Generative Models
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Wan: Open and Advanced Large-Scale Video Generative Models