update dependent

torchpipe · Jan 17, 2024 · 8e39f9d · 8e39f9d
1 parent 3819ea2
commit 8e39f9d
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 4 deletions.
diff --git a/docs/installation.mdx b/docs/installation.mdx
@@ -14,9 +14,9 @@ The basic environment is as follows:
 | Dependency         | Version           | Remarks                                                                                                                                                                                                                                                    |
 |--------------------|:------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | `cuda`             | >= 11.0           | - The CUDA version must be consistent with the version that PyTorch depends on (for the convenience of `torch.utils.cpp_extension` to compile code on the fly). <br />- Compatibility testing with CUDA 10.2(no support for c++17) is no longer performed. |
-| `pytorch`          | >= 1.10.0(cuda11) | - Compatibility testing is no longer performed for `c++14/cuda-10.2/pytorch==1.10.2`, but you may still be able to run it with simple modifications.                                                                                                       |
+| `pytorch`          | >= 1.10.2(cuda11) | - Compatibility testing is no longer performed for `c++14/cuda-10.2/pytorch==1.10.2`, but you may still be able to run it with simple modifications.                                                                                                       |
 | `opencv`(optional) | 4.x               | At least the core, imgproc, imgcodecs, and highgui modules are included.                                                                                                                                                                                   |
-|  `tensorrt`(optional)	|>= 7.2<br /><= 9.1.0.4| - There is a [memory leak](https://github.com/NVIDIA/TensorRT/issues/351) in TensorRT 7.0 with dynamic inputs.<br />- TensorRT 7.1 and earlier cannot directly INT8-quantize models with dynamic inputs.
+|  `tensorrt`(optional)	|>= 7.2<br /><= 9.2| - There is a [memory leak](https://github.com/NVIDIA/TensorRT/issues/351) in TensorRT 7.0 with dynamic inputs.
 
 
 :::note 
@@ -28,6 +28,10 @@ The easiest way is to choose NGC mirror for source code compilation (official mi
 
 - Minimum support nvcr.io/nvidia/pytorch:21.07-py3 (Starting from 0.3.2rc3)
 - Maximum support nvcr.io/nvidia/pytorch:23.08-py3
+- Latest test version: nvcr.io/nvidia/pytorch:22.12-py3
+
+If you encounter any compilation or runtime issues inside the Docker container, please submit an issue.
+
 
 First, clone the code:
 

diff --git a/i18n/zh/docusaurus-plugin-content-docs/current/installation.mdx b/i18n/zh/docusaurus-plugin-content-docs/current/installation.mdx
@@ -15,9 +15,9 @@ type: explainer
 | 依赖             | 版本                   | 备注                                                                                                                                          |
 |------------------|:-----------------------|---------------------------------------------------------------------------------------------------------------------------------------------|
 | `cuda`           | >= 11.0                | - 与PyTorch依赖的cuda版本必须一致（便于`torch.utils.cpp_extension`即时编译代码） <br />- 不再对CUDA 10.2（不支持c++17）的兼容进行测试。            |
-| `pytorch`        | >= 1.10.0（cuda11）      | - 对于`c++14/cuda-10.2/pytorch==1.10.2`不再进行兼容测试，然而通过简单修改，您可能仍可运行。                                                      |
+| `pytorch`        | >= 1.10.2（cuda11）      | - 对于`c++14/cuda-10.2/pytorch==1.10.2`不再进行兼容测试，然而通过简单修改，您可能仍可运行。                                                      |
 | `opencv`(可选)   | 3.x, 4.x               | 至少包含 core, imgproc，imgcodecs 和 highgui 四个模块                                                                                          |
-| `tensorrt`(可选) | >= 7.2(Starting from 0.3.2rc3)<br /><= 9.1.0.4 | - tensorrt 7.0 动态输入下存在[内存泄漏](https://github.com/NVIDIA/TensorRT/issues/351)<br />- tensorrt 7.1 及以下无法直接int8化动态输入的模型 |
+| `tensorrt`(可选) | >= 7.2(Starting from 0.3.2rc3)<br /><= 9.2 | - tensorrt 7.0 动态输入下存在[内存泄漏](https://github.com/NVIDIA/TensorRT/issues/351) |
 
 :::note 
 以上依赖项均来源于默认存在的特定计算后端。构筑c++核心不依赖于以上任意一项。
@@ -27,6 +27,9 @@ type: explainer
 最简单的方式是可以选择<font color='Brown'>NGC镜像</font>进行源码编译（低版本驱动依靠 Forward Compatibility 或者 Minor Version Compatibility 依然可能跑起来官方镜像）。
 - 最低支持 nvcr.io/nvidia/pytorch:21.07-py3（从0.3.2rc3开始）
 - 最高支持 nvcr.io/nvidia/pytorch:23.08-py3
+- 测试版本 nvcr.io/nvidia/pytorch:22.12-py3
+
+如果在docker容器内遇到编译或者运行问题，请提交issue。
 
 首先，克隆代码：