bump version to v0.7.0.post3 (#3115)

README.md

@@ -23,7 +23,7 @@ ______________________________________________________________________
 
 ## Latest News 🎉
 
-<details open>
+<details close>
 <summary><b>2024</b></summary>
 
 - \[2024/11\] Support Mono-InternVL with PyTorch engine
@@ -91,14 +91,6 @@ LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by
 
 ![v0 1 0-benchmark](https://github.com/InternLM/lmdeploy/assets/4560679/8e455cf1-a792-4fa8-91a2-75df96a2a5ba)
 
-For detailed inference benchmarks in more devices and more settings, please refer to the following link:
-
-- [A100](./docs/en/benchmark/a100_fp16.md)
-- V100
-- 4090
-- 3090
-- 2080
-
 # Supported Models
 
 <table>
@@ -160,6 +152,7 @@ For detailed inference benchmarks in more devices and more settings, please refe
   <li>DeepSeek-VL (7B)</li>
   <li>InternVL-Chat (v1.1-v1.5)</li>
   <li>InternVL2 (1B-76B)</li>
+  <li>InternVL2.5(MPO) (1B-78B)</li>
   <li>Mono-InternVL (2B)</li>
   <li>ChemVLM (8B-26B)</li>
   <li>MiniGeminiLlama (7B)</li>

README_ja.md

@@ -23,7 +23,7 @@ ______________________________________________________________________
 
 ## 最新ニュース 🎉
 
-<details open>
+<details close>
 <summary><b>2024</b></summary>
 
 - \[2024/08\] 🔥🔥 LMDeployは[modelscope/swift](https://github.com/modelscope/swift)に統合され、VLMs推論のデフォルトアクセラレータとなりました
@@ -89,13 +89,6 @@ LMDeploy TurboMindエンジンは卓越した推論能力を持ち、さまざ
 
 ![v0 1 0-benchmark](https://github.com/InternLM/lmdeploy/assets/4560679/8e455cf1-a792-4fa8-91a2-75df96a2a5ba)
 
-詳細な推論ベンチマークについては、以下のリンクを参照してください：
-
-- [A100](./docs/en/benchmark/a100_fp16.md)
-- 4090
-- 3090
-- 2080
-
 # サポートされているモデル
 
 <table>
@@ -156,6 +149,7 @@ LMDeploy TurboMindエンジンは卓越した推論能力を持ち、さまざ
   <li>DeepSeek-VL (7B)</li>
   <li>InternVL-Chat (v1.1-v1.5)</li>
   <li>InternVL2 (1B-76B)</li>
+  <li>InternVL2.5(MPO) (1B-78B)</li>
   <li>Mono-InternVL (2B)</li>
   <li>ChemVLM (8B-26B)</li>
   <li>MiniGeminiLlama (7B)</li>

README_zh-CN.md

@@ -23,7 +23,7 @@ ______________________________________________________________________
 
 ## 最新进展 🎉
 
-<details open>
+<details close>
 <summary><b>2024</b></summary>
 
 - \[2024/11\] PyTorch engine 支持 Mono-InternVL 模型
@@ -93,13 +93,6 @@ LMDeploy TurboMind 引擎拥有卓越的推理能力，在各种规模的模型
 
 ![v0 1 0-benchmark](https://github.com/InternLM/lmdeploy/assets/4560679/8e455cf1-a792-4fa8-91a2-75df96a2a5ba)
 
-更多设备、更多计算精度、更多setting下的的推理 benchmark，请参考以下链接：
-
-- [A100](./docs/en/benchmark/a100_fp16.md)
-- 4090
-- 3090
-- 2080
-
 # 支持的模型
 
 <table>
@@ -161,6 +154,7 @@ LMDeploy TurboMind 引擎拥有卓越的推理能力，在各种规模的模型
   <li>DeepSeek-VL (7B)</li>
   <li>InternVL-Chat (v1.1-v1.5)</li>
   <li>InternVL2 (1B-76B)</li>
+  <li>InternVL2.5(MPO) (1B-78B)</li>
   <li>Mono-InternVL (2B)</li>
   <li>ChemVLM (8B-26B)</li>
   <li>MiniGeminiLlama (7B)</li>

docs/en/get_started/installation.md

@@ -23,7 +23,7 @@ pip install lmdeploy
 The default prebuilt package is compiled on **CUDA 12**. If CUDA 11+ (>=11.3) is required, you can install lmdeploy by:
 
 ```shell
-export LMDEPLOY_VERSION=0.7.0.post2
+export LMDEPLOY_VERSION=0.7.0.post3
 export PYTHON_VERSION=38
 pip install https://github.com/InternLM/lmdeploy/releases/download/v${LMDEPLOY_VERSION}/lmdeploy-${LMDEPLOY_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux2014_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu118
 ```

docs/zh_cn/get_started/installation.md

@@ -23,7 +23,7 @@ pip install lmdeploy
 默认的预构建包是在 **CUDA 12** 上编译的。如果需要 CUDA 11+ (>=11.3)，你可以使用以下命令安装 lmdeploy：
 
 ```shell
-export LMDEPLOY_VERSION=0.7.0.post2
+export LMDEPLOY_VERSION=0.7.0.post3
 export PYTHON_VERSION=38
 pip install https://github.com/InternLM/lmdeploy/releases/download/v${LMDEPLOY_VERSION}/lmdeploy-${LMDEPLOY_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux2014_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu118
 ```

lmdeploy/version.py

@@ -1,7 +1,7 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 from typing import Tuple
 
-__version__ = '0.7.0.post2'
+__version__ = '0.7.0.post3'
 short_version = __version__