Stars
The simplest, fastest repository for training/finetuning small-sized VLMs.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
The official Python SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
Open source software that helps you create and deploy high-frequency crypto trading bots
OpenCL integration for Python, plus shiny features
CUDA integration for Python, plus shiny features
Build effective agents using Model Context Protocol and simple workflow patterns
Efficient and easy multi-instance LLM serving
Python implementation of AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
A live stream development of RL tunning for LLM agents
No fortress, purely open ground. OpenManus is Coming.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Inference service for Qwen2.5-VL-7b model
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Train transformer language models with reinforcement learning.
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …
An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Witness the aha moment of VLM with less than $3.
Ongoing research training transformer models at scale
Fully open reproduction of DeepSeek-R1
Stateful load balancer custom-tailored for llama.cpp 🏓🦙
ICIP 2022: Adaptive Radial Projection on Fourier Magnitude Spectrum for Document Image Skew Estimation