Python logging made (stupidly) simple

Implementation of a local in-memory cache for Triton Inference Server's TRITONCACHE API

ModelScope: bring the notion of Model-as-a-Service to life.

Anbox is a container-based approach to boot a full Android system on a regular GNU/Linux system

Unofficial faiss wheel builder

Redis Vector Library (RedisVL) interfaces with Redis' vector database for realtime semantic search, RAG, and recommendation systems.

🦄🔒 Awesome list of secrets in environment variables 🖥️

the AI-native open-source embedding database

Generic helm chart for all kind of applications

Redis client written in C++

Rapid fuzzy string matching in Python using various string metrics

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

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

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Fast and memory-efficient exact attention

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

Python bindings for llama.cpp

Build Conversational AI in minutes ⚡️

LLM inference in C/C++

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Full-featured and highly configurable SFTP, HTTP/S, FTP/S and WebDAV server - S3, Google Cloud Storage, Azure Blob

Open Source Continuous File Synchronization

aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.

Provision infrastructure and install OpenShift 3.

Google's Operations Research tools:

⚡ Langchain apps in production using Jina & FastAPI

Vertica dialect for SQLAlchemy using the vertica-python client