Stars
自我进化，个人、家庭、工作三位一体 爱 健康 财富 是人生值得追求的东西！人生不过是一段体验。我们都是时间的囚徒，活在当下。有趣！有料！
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
Synthetic data curation for post-training and structured data extraction
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)
Conversational RPA SDK for Chatbot Makers. Join our Discord: https://discord.gg/7q8NBZbQzt
Build production-ready AI agents in both Python and Typescript.
Enjoy the magic of Diffusion models!
SoraWebui is an open-source Sora web client, enabling users to easily create videos from text with OpenAI's Sora model.
An educational resource to help anyone learn deep reinforcement learning.
verl: Volcano Engine Reinforcement Learning for LLMs
A Datacenter Scale Distributed Inference Serving Framework
Latency and Memory Analysis of Transformer Models for Training and Inference
DeepSeek-V3/R1 inference performance simulator
Flops counter for neural networks in pytorch framework
Open-Sora: Democratizing Efficient Video Production for All
Cost-efficient and pluggable Infrastructure components for GenAI inference
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
FlashInfer: Kernel Library for LLM Serving
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
FlashMLA: Efficient Multi-head Latent Attention Kernels
SGLang is a high-performance serving framework for large language models and multimodal models.
Fully open reproduction of DeepSeek-R1