mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[Doc] Update docs for v2.3.0rc0 (#4828)
* [Doc] Update docs for v2.3.0rc0 * [Doc] Update docs for v2.3.0rc0 * [Doc] Update docs for v2.3.0rc0 * Update README_CN.md * Add deployment guide link for FastDeploy v2.3-rc0 Updated release note for FastDeploy v2.3-rc0 to include deployment guide link. * Add Deployment Guide link for FastDeploy v2.3-rc0 Updated the news section to include a link to the Deployment Guide for FastDeploy v2.3-rc0. --------- Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
This commit is contained in:
@@ -26,12 +26,13 @@
|
||||
# FastDeploy :基于飞桨的大语言模型与视觉语言模型推理部署工具包
|
||||
|
||||
## 最新活动
|
||||
**[2025-09] 🔥 FastDeploy v2.2 全新发布**: HuggingFace生态模型兼容,性能进一步优化,更新增对[baidu/ERNIE-21B-A3B-Thinking](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking)支持!
|
||||
|
||||
**[2025-11]** 🔥FastDeploy v2.3-rc0 PaddleOCR-VL 0.9B推理性能专项优化发布,**相比vLLM吞吐提升35%**
|
||||
|
||||
**[2025-09] FastDeploy v2.2 全新发布**: HuggingFace生态模型兼容,性能进一步优化,更新增对[baidu/ERNIE-21B-A3B-Thinking](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking)支持!
|
||||
|
||||
**[2025-08] FastDeploy v2.1 发布**:全新的KV Cache调度策略,更多模型支持PD分离和CUDA Graph,昆仑、海光等更多硬件支持增强,全方面优化服务和推理引擎的性能。
|
||||
|
||||
**[2025-07] 《FastDeploy2.0推理部署实测》专题活动已上线!** 完成文心4.5系列开源模型的推理部署等任务,即可获得骨瓷马克杯等FastDeploy2.0官方周边及丰富奖金!🎁 欢迎大家体验反馈~ 📌[报名地址](https://www.wjx.top/vm/meSsp3L.aspx#) 📌[活动详情](https://github.com/PaddlePaddle/FastDeploy/discussions/2728)
|
||||
|
||||
## 关于
|
||||
|
||||
**FastDeploy** 是基于飞桨(PaddlePaddle)的大语言模型(LLM)与视觉语言模型(VLM)推理部署工具包,提供**开箱即用的生产级部署方案**,核心技术特性包括:
|
||||
|
||||
Reference in New Issue
Block a user