Tags: #high-performance

SGLang is a high-performance serving framework for large language models and multimodal models, optimizing inference throughput and latency.

A high-performance inference and deployment toolkit for Large Language Models (LLMs) and Vision-Language Models (VLMs) based on PaddlePaddle.

A KVCache-centric disaggregated architecture for high-performance LLM serving, powering leading AI services.

Vortex is a next-generation, high-performance, and extensible open-source columnar file format and toolkit designed for blazing-fast data processing and storage, especially with object storage.

A modular, high-performance web UI for AI image and video generation, emphasizing accessible powertools and extensibility.

A lightweight, high-performance, and secure reverse proxy written in Rust, designed to expose services behind NAT to the internet.

QuestDB is an open-source, high-performance time-series database designed for blazingly fast ingestion and low-latency SQL queries.

Zvec is a lightweight, lightning-fast, in-process vector database built on Alibaba's Proxima, enabling scalable and low-latency similarity search directly within applications.

A high performance real-time analytics database designed for fast queries on large datasets.

A high-performance distributed file system optimized for AI training and inference workloads, leveraging modern SSDs and RDMA networks for scalable and consistent storage.