From fd143bfc9621d564d44fd4d8410ad01ab3dc8f7a Mon Sep 17 00:00:00 2001 From: pa <1020401660@qq.com> Date: Fri, 24 Jul 2026 17:43:00 +0800 Subject: [PATCH] doc: Enhance README with project overview and capabilities Updated project description and added a new overview of Fluxon's capabilities. --- README.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 9adafb2..c7bd3bc 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,8 @@
+One unified system for high performance RPC, KV Cache, Message Queue, and File & Object Acceleration. + [![Linux Only](https://img.shields.io/badge/Linux-Only-2ea44f)](#runtime-requirements) [![Python](https://img.shields.io/badge/Python-%3E%3D3.10-3776AB)](#runtime-requirements) [![Rust](https://img.shields.io/badge/Rust-1.93.0-000000)](./fluxon_rs/rust-toolchain.toml) @@ -21,9 +23,10 @@ Add the project administrator on WeChat to join the open-source community group. [English](./README.md) | [中文](./README_CN.md) | [Docs](https://tele-ai.github.io/Fluxon/) | [中文文档](https://tele-ai.github.io/Fluxon/cn/) | GitHub repository +
-Fluxon is a high-performance distributed data acceleration plane for AI workloads, providing unified caching, communication, and storage acceleration for inference KV Cache, training & data processing. Built on the unified Rust-based transport and caching foundation, Fluxon exposes three standardized interfaces that target the core bottlenecks in AI systems: +Built on the unified Rust-based transport and caching foundation, Fluxon exposes three standardized interfaces that target the core bottlenecks in AI systems: - **KV/RPC (Unified key-value and RPC)**: Breaks data silos and enables efficient cross-process, cross-node reuse of inference-side `KV Cache` and `latent cache` - **MQ (Elastic message queue)**: Decouples system dependencies and supports elastic message transport across heterogeneous resource pools