Stars
A golang-based data loader which can be used from Python. Focused on a VectorDB stack at the moment, fetching and processing data per sample at GB/s speeds.
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
aider is AI pair programming in your terminal
Efficient Triton Kernels for LLM Training
FlashInfer: Kernel Library for LLM Serving
A throughput-oriented high-performance serving framework for LLMs
RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
Efficient and general syntactical decoding for Large Language Models
BullMQ - Message Queue and Batch processing for NodeJS and Python based on Redis
Build AI Assistants with memory, knowledge and tools.
Run PyTorch LLMs locally on servers, desktop and mobile
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
GPTQ based LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
基于python的网页自动化工具。既能控制浏览器，也能收发数据包。可兼顾浏览器自动化的便利性和requests的高效率。功能强大，内置无数人性化设计和便捷功能。语法简洁而优雅，代码量少。
Composio equip's your AI agents & LLMs with 100+ high-quality integrations via function calling
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
The lightweight, user-friendly, distributed relational database built on SQLite.
🛏 An HTML to Markdown converter written in JavaScript