From 8d45c25f2ad45cd524e0327d4ae198ee07b35231 Mon Sep 17 00:00:00 2001 From: irexyc Date: Thu, 18 May 2023 14:12:30 +0800 Subject: [PATCH] update docs --- docs/en/02-how-to-run/triton_server.md | 4 ++++ docs/zh_cn/02-how-to-run/triton_server.md | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/docs/en/02-how-to-run/triton_server.md b/docs/en/02-how-to-run/triton_server.md index 7652d47755..a8fe4b1df1 100644 --- a/docs/en/02-how-to-run/triton_server.md +++ b/docs/en/02-how-to-run/triton_server.md @@ -29,6 +29,10 @@ a) Using Docker images For ease of use, we provide a Docker image to support the deployment of models converted by MMDeploy. The image supports Tensorrt and ONNX Runtime as backends. If you need other backends, you can choose build from source. +``` +docker run -it --rm --gpus all openmmlab/mmdeploy:triton-22.12 +``` + b) Build from source You can refer [build from source](../01-how-to-build/build_from_source.md) to build MMDeploy. In order to build MMDeploy Triton Backend, you need to add `-DTRITON_MMDEPLOY_BACKEND=ON` to cmake configure command. By default, the latest version of Triton Backend is used. If you want to use an older version of Triton Backend, you can add `-DTRITON_TAG=r22.12` to the cmake configure command. diff --git a/docs/zh_cn/02-how-to-run/triton_server.md b/docs/zh_cn/02-how-to-run/triton_server.md index d9097252ca..bc25d6da03 100644 --- a/docs/zh_cn/02-how-to-run/triton_server.md +++ b/docs/zh_cn/02-how-to-run/triton_server.md @@ -29,6 +29,10 @@ a) 使用 Docker 镜像 为了方便使用，我们提供了 Docker 镜像，支持对通过 MMDeploy 转换的模型进行部署。镜像支持 Tensorrt 以及 ONNX Runtime 作为后端。若需要其他后端，可选择从源码进行编译。 +``` +docker run -it --rm --gpus all openmmlab/mmdeploy:triton-22.12 +``` + b) 从源码编译 从源码编译 MMDeploy 的方式可参考[源码手动安装](../01-how-to-build/build_from_source.md)，要编译 MMDeploy Triton Backend，需要在编译命令中添加：`-DTRITON_MMDEPLOY_BACKEND=ON`。默认使用最新版本的 Triton Backend，若要使用旧版本的 Triton Backend，可在编译命令中添加`-DTRITON_TAG=r22.12`