docs : add project capability overview

- summarize the end-to-end model lifecycle
- add matching capability tables in both READMEs

README.md

@@ -27,7 +27,7 @@
 
 ## 📖 Table of Contents
 
-- [Features](#features)
+- [Overview](#overview)
 - [Getting Started](#getting-started)
 - [Demo](#demo)
 - [Documentation](#documentation)
@@ -40,15 +40,19 @@
 <a id="english"></a>
 ## English
 
-### Features
+### Overview
 
-- 🚀 **High Performance**: Optimized for both training and inference with efficient parallelization.
-- 🔧 **Flexible**: Support for seq/sft/dpo/grpo training, customizable model architectures.
-- 💡 **Easy to Use**: Simple API with comprehensive examples and demos.
-- 📦 **Lightweight**: Minimal dependencies, easy to deploy.
-- 🔬 **Research‑Friendly**: Modular design, easy to experiment with new ideas.
-- 🤗 **HuggingFace-Style API**: AutoModel/AutoTokenizer APIs inspired by HuggingFace for easy model and tokenizer loading.
-- 🔌 **Dual API Compatibility**: Supports both OpenAI and Anthropic chat completion APIs out of the box.
+AstrAI is an end-to-end framework for building, training, evaluating, and serving bilingual Chinese-English Transformer models. It provides a compact PyTorch codebase for the complete model lifecycle, from declarative data preprocessing and distributed training to continuous-batching inference and OpenAI/Anthropic-compatible APIs.
+
+| Area | Capabilities |
+|---|---|
+| **Models** | Autoregressive language models and embedding models with GQA, MLA, MoE, RoPE, and extensible attention/FFN components |
+| **Training** | Pre-training (`seq`), supervised fine-tuning (`sft`), DPO, and GRPO with gradient accumulation, checkpointing, DDP, and FSDP |
+| **Data** | Declarative JSON preprocessing, configurable masking and packing, binary/JSONL storage, and streaming datasets |
+| **Inference** | Continuous batching, paged KV cache, prefix caching, streaming generation, and Torch/CUDA/FlashAttention backends |
+| **Serving** | FastAPI server with OpenAI and Anthropic chat completion protocols, including SSE streaming and tool calls |
+| **Evaluation** | Perplexity, MMLU, HumanEval, IFEval, IFD, and ROUGE evaluation tools |
+| **Extensibility** | Factory and registry architecture for models, datasets, training strategies, callbacks, kernels, and protocol components |
 
 ### Getting Started
 

docs/README-zh-CN.md

@@ -33,7 +33,7 @@
 
 ## 📖 目录
 
-- [特性](#特性)
+- [项目概览](#项目概览)
 - [快速上手](#快速上手)
 - [演示](#演示)
 - [文档](#文档)
@@ -46,15 +46,19 @@
 <a id="chinese"></a>
 ## 中文
 
-### 特性
+### 项目概览
 
-- 🚀 **高性能**: 训练与推理双向优化，高效并行。
-- 🔧 **灵活**: 支持 seq/sft/dpo/grpo 多种训练方式，可定制模型架构。
-- 💡 **易用**: 简洁的 API 与丰富的示例、演示。
-- 📦 **轻量**: 依赖少，部署简单。
-- 🔬 **研究友好**: 模块化设计，便于实验新想法。
-- 🤗 **HuggingFace 风格 API**: 类 HuggingFace 的 AutoModel/AutoTokenizer 接口，方便加载模型和分词器。
-- 🔌 **双 API 兼容**: 同时支持 OpenAI 和 Anthropic 聊天补全 API，开箱即用。
+AstrAI 是一个面向中英双语 Transformer 模型的端到端框架，覆盖模型构建、训练、评测与部署。项目以精简的 PyTorch 代码实现完整模型生命周期，包括声明式数据预处理、分布式训练、连续批处理推理，以及兼容 OpenAI 和 Anthropic 的服务接口。
+
+| 领域 | 能力 |
+|---|---|
+| **模型** | 自回归语言模型与嵌入模型，支持 GQA、MLA、MoE、RoPE，以及可扩展的 Attention/FFN 组件 |
+| **训练** | 预训练（`seq`）、监督微调（`sft`）、DPO 和 GRPO，支持梯度累积、检查点、DDP 与 FSDP |
+| **数据** | 声明式 JSON 预处理、可配置掩码与样本打包、二进制/JSONL 存储和流式数据集 |
+| **推理** | 连续批处理、分页 KV Cache、前缀缓存、流式生成，以及 Torch/CUDA/FlashAttention 后端 |
+| **服务** | 基于 FastAPI 的 OpenAI 与 Anthropic 聊天补全协议，支持 SSE 流式输出和工具调用 |
+| **评测** | Perplexity、MMLU、HumanEval、IFEval、IFD 和 ROUGE 评测工具 |
+| **扩展** | 基于工厂与注册表扩展模型、数据集、训练策略、回调、内核和协议组件 |
 
 ### 快速上手