From 4626815b568b9e656bc7cda116d053ccec3f8f84 Mon Sep 17 00:00:00 2001 From: jhqxxx <18280426169@163.com> Date: Tue, 31 Mar 2026 21:22:07 +0800 Subject: [PATCH] update doc --- README.md | 57 ++++++++++++++++++++----------------------------- README.zh-CN.md | 56 ++++++++++++++++++++---------------------------- 2 files changed, 46 insertions(+), 67 deletions(-) diff --git a/README.md b/README.md index 574b742..f82f9d8 100644 --- a/README.md +++ b/README.md @@ -45,6 +45,29 @@ aha is a high-performance, cross-platform AI inference engine built with Rust an - **🛡️ Memory Safe** — Built with Rust for reliability - **🧠 Attention Optimization** - Optional Flash Attention support for optimized long sequence processing +## Changelog + +### 2026-03-31 +- add server adn cli mod +- aha model name use modelscope id replace +- update WhichModel +- Usage add time info +- dependencies delete aha_openai_dive,chrono + +### v0.2.5 (2026-03-30) +- add LFM2.5VL-1.6B +- add LFM2VL-1.6B + +### v0.2.4 (2026-03-23) +- add LFM2.5-1.2B-Instruct +- add LFM2-1.2B + +### v0.2.3 (2026-03-18) +- add DeepSeek-OCR-2 + +**[View full changelog](docs/changelog.md)** → + + ## Quick Start ### Installation @@ -111,40 +134,6 @@ curl http://localhost:10100/v1/chat/completions \ ' ``` -## Changelog - -### 2026-03-31 -- add server adn cli mod -- aha model name use modelscope id replace -- update WhichModel -- Usage add time info -- dependencies delete aha_openai_dive,chrono - -### v0.2.5 (2026-03-30) -- add LFM2.5VL-1.6B -- add LFM2VL-1.6B - -### v0.2.4 (2026-03-23) -- add LFM2.5-1.2B-Instruct -- add LFM2-1.2B - -### v0.2.3 (2026-03-18) -- add DeepSeek-OCR-2 - -### 2026-03-17 -- add PaddleOCR-VL1.5 model -- fix qwen3.5 position_ids create bug -- cli param add - - gguf_path: Local GGUF model weight path (required for loading models with GGUF) - - mmproj_path: Local path to mmproj GGUF weights (required for multimodal GGUF loading) -- WhichModel add qwen3.5-gguf - -### 2026-03-16 -- Added Qwen3.5 mmproj - -**[View full changelog](docs/changelog.md)** → - - ## Documentation | Document | Description | diff --git a/README.zh-CN.md b/README.zh-CN.md index 88c93b0..f094f2d 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -44,6 +44,29 @@ aha 是一款基于 Rust 和 Candle 框架构建的高性能跨平台 AI 推理 - **🛡️ 内存安全** — Rust 构建,稳定可靠 - **🧠 注意力优化** - 可选 Flash Attention 支持,优化长序列处理 +## 更新日志 + +### 2026-03-31 +- 新增 server 和 cli 模块 +- aha模型名称使用 modelscope id 替换 +- 更新 WhichModel 枚举 +- Usage 增加时间信息 +- 删除 aha_openai_dive, chrono 依赖 + +### v0.2.5 (2026-03-30) +- 新增 LFM2.5VL-1.6B +- 新增 LFM2VL-1.6B + +### v0.2.4 (2026-03-23) +- 新增 LFM2.5-1.2B-Instruct +- 新增 LFM2-1.2B + +### v0.2.3 (2026-03-18) +- 新增 DeepSeek-OCR-2 + +**[查看完整更新日志](docs/changelog.zh-CN.md)** → + + ## 快速开始 ### 安装 @@ -109,39 +132,6 @@ curl http://localhost:10100/v1/chat/completions \ }' ``` -## 更新日志 - -### 2026-03-31 -- 新增 server 和 cli 模块 -- aha模型名称使用 modelscope id 替换 -- 更新 WhichModel 枚举 -- Usage 增加时间信息 -- 删除 aha_openai_dive, chrono 依赖 - -### v0.2.5 (2026-03-30) -- 新增 LFM2.5VL-1.6B -- 新增 LFM2VL-1.6B - -### v0.2.4 (2026-03-23) -- 新增 LFM2.5-1.2B-Instruct -- 新增 LFM2-1.2B - -### v0.2.3 (2026-03-18) -- 新增 DeepSeek-OCR-2 - -### 2026-03-17 -- 新增 PaddleOCR-VL1.5 模型 -- 修复 qwen3.5 position_ids 创建错误 -- cli 参数增加 - - gguf_path: 本地 GGUF 模型权重路径(加载 GGUF 模型时需要) - - mmproj_path: 本地 mmproj GGUF 权重路径(加载多模态 GGUF 时需要) -- WhichModel 增加 qwen3.5-gguf - -### 2026-03-16 -- 增加 Qwen3.5 mmproj - -**[查看完整更新日志](docs/changelog.zh-CN.md)** → - ## 文档 | 文档 | 描述 |