init v0.23.0

Signed-off-by: Sun Ruoxi <sunruoxi@4paradigm.com>
2026-08-27 15:11:51 +08:00
parent b582a8e7d1
commit 7f8a1b1f7a
2849 changed files with 712887 additions and 22001 deletions
--- a/docs/source/locale/zh_CN/LC_MESSAGES/quick_start.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/quick_start.po
@@ -2,148 +2,403 @@
 # Copyright (C) 2025, vllm-ascend team
 # This file is distributed under the same license as the vllm-ascend
 # package.
-# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2026.
 #
 #, fuzzy
 msgid ""
 msgstr ""
 "Project-Id-Version: vllm-ascend\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-07-18 09:01+0800\n"
-"PO-Revision-Date: 2025-07-18 10:09+0800\n"
-"Last-Translator: \n"
+"POT-Creation-Date: 2026-08-08 05:20+0000\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: zh_CN <LL@li.org>\n"
 "Language: zh_CN\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
 "Plural-Forms: nplurals=1; plural=0;\n"
-"Generated-By: Babel 2.17.0\n"
-"X-Generator: Poedit 3.5\n"
+"Generated-By: Babel 2.18.0\n"

-#: ../../quick_start.md:1
+#: ../../source/quick_start.md:1
 msgid "Quickstart"
 msgstr "快速入门"

-#: ../../quick_start.md:3
-msgid "Prerequisites"
-msgstr "先决条件"
+#: ../../source/quick_start.md:3
+msgid "Introduction"
+msgstr "简介"

-#: ../../quick_start.md:5
+#: ../../source/quick_start.md:5
+msgid ""
+"This section guides you through container-based environment setup and large "
+"model inference, using the Qwen3-0.6B offline single-GPU inference script as"
+" an example."
+msgstr "本节以Qwen3-0.6B离线单GPU推理脚本为例，指导您完成基于容器的环境搭建和大模型推理。"
+
+#: ../../source/quick_start.md:7
+msgid ""
+"For details on using different models, see the corresponding model tutorial "
+"in the \"Model Tutorials\" directory, for example, "
+"[Qwen3-30B-A3B](../../docs/source/tutorials/models/Qwen3-30B-A3B.md)."
+msgstr ""
+"关于不同模型的使用详情，请参见\"模型教程\"目录中对应的模型教程，例如[Qwen3-30B-A3B](../../docs/source/tutorials/models/Qwen3-30B-A3B.md)。"
+
+#: ../../source/quick_start.md:8
+msgid ""
+"For details on using different functions, see the corresponding function "
+"tutorial in the \"Function Tutorials\" directory, for example, [Prefill-"
+"Decode Disaggregation "
+"(DeepSeek)](../../docs/source/tutorials/features/pd_disaggregation_mooncake_multi_node.md)."
+msgstr ""
+"有关使用不同功能的详细信息，请参阅“功能教程”目录中相应的功能教程，例如，[预填充-"
+"解码分离（DeepSeek）](../../docs/source/tutorials/features/pd_disaggregation_mooncake_multi_node.md)。"
+
+#: ../../source/quick_start.md:10
+msgid "Prerequisites"
+msgstr "前提条件"
+
+#: ../../source/quick_start.md:12
 msgid "Supported Devices"
 msgstr "支持的设备"

-#: ../../quick_start.md:6
+#: ../../source/quick_start.md:14
 msgid ""
-"Atlas A2 Training series (Atlas 800T A2, Atlas 900 A2 PoD, Atlas 200T A2 "
+"Atlas A2 training series (Atlas 800T A2, Atlas 900 A2 PoD, Atlas 200T A2 "
 "Box16, Atlas 300T A2)"
 msgstr ""
-"Atlas A2 训练系列（Atlas 800T A2，Atlas 900 A2 PoD，Atlas 200T A2 Box16，"
-"Atlas 300T A2）"
+"Atlas A2训练系列（Atlas 800T A2、Atlas 900 A2 PoD、Atlas 200T A2 Box16、Atlas 300T "
+"A2）"

-#: ../../quick_start.md:7
-msgid "Atlas 800I A2 Inference series (Atlas 800I A2)"
-msgstr "Atlas 800I A2 推理系列（Atlas 800I A2）"
+#: ../../source/quick_start.md:15
+msgid "Atlas 800I A2 inference series (Atlas 800I A2)"
+msgstr "Atlas 800I A2推理系列（Atlas 800I A2）"

-#: ../../quick_start.md:9
+#: ../../source/quick_start.md:16
+msgid ""
+"Atlas A3 training series (Atlas 800T A3, Atlas 900 A3 SuperPoD, Atlas 9000 "
+"A3 SuperPoD)"
+msgstr ""
+"Atlas A3训练系列（Atlas 800T A3、Atlas 900 A3 SuperPoD、Atlas 9000 A3 SuperPoD）"
+
+#: ../../source/quick_start.md:17
+msgid "Atlas 800I A3 inference series (Atlas 800I A3)"
+msgstr "Atlas 800I A3推理系列（Atlas 800I A3）"
+
+#: ../../source/quick_start.md:18
+msgid "Atlas 950DT inference series (Atlas 950DT)"
+msgstr "Atlas 950DT推理系列（Atlas 950DT）"
+
+#: ../../source/quick_start.md ../../source/quick_start.md:19
+msgid "Atlas 300I DUO"
+msgstr "Atlas 300I DUO"
+
+#: ../../source/quick_start.md:20
+msgid "Atlas 200I Pro"
+msgstr "Atlas 200I Pro"
+
+#: ../../source/quick_start.md:22
+msgid "Requirements"
+msgstr "要求"
+
+#: ../../source/quick_start.md
+msgid "Atlas A2/A3/950DT inference products"
+msgstr "Atlas A2/A3/950DT推理产品"
+
+#: ../../source/quick_start.md:28
+msgid "OS: Linux"
+msgstr "操作系统：Linux"
+
+#: ../../source/quick_start.md:29
+msgid "Python: >= 3.10, < 3.13"
+msgstr "Python：>= 3.10，< 3.13"
+
+#: ../../source/quick_start.md:30
+msgid "Hardware with Ascend NPUs. It's usually the Atlas 800 A2 series."
+msgstr "配备昇腾NPU的硬件，通常为Atlas 800 A2系列。"
+
+#: ../../source/quick_start.md:31
+msgid "Software:"
+msgstr "软件："
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Software"
+msgstr "软件"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Supported version"
+msgstr "支持的版本"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Note"
+msgstr "注意"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Ascend HDK"
+msgstr "Ascend HDK"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid ""
+"Refer to the [CANN 9.1.0 Release "
+"Notes](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/910/softwareinst/releasenote/9.1.0/release-"
+"notes.md)"
+msgstr ""
+"请参阅 [CANN 9.1.0 "
+"版本说明](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/910/softwareinst/releasenote/9.1.0/release-"
+"notes.md)"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Required for CANN"
+msgstr "CANN 所需"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "CANN"
+msgstr "CANN"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "== 9.1.0"
+msgstr "== 9.1.0"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Required for vllm-ascend and TorchNPU"
+msgstr "vllm-ascend 和 TorchNPU 所需"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "TorchNPU"
+msgstr "TorchNPU"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "== 2.10.0.post4"
+msgstr "== 2.10.0.post4"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid ""
+"Required for vllm-ascend, No need to install manually, it will be auto "
+"installed in below steps"
+msgstr "vllm-ascend 所需，无需手动安装，将在以下步骤中自动安装"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "torch"
+msgstr "torch"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "== 2.10.0"
+msgstr "== 2.10.0"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid ""
+"Required for TorchNPU and vllm, No need to install manually, it will be auto"
+" installed in below steps"
+msgstr "TorchNPU 和 vllm 所需，无需手动安装，将在以下步骤中自动安装"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "NNAL"
+msgstr "NNAL"
+
+#: ../../source/quick_start.md:33 ../../source/quick_start.md:53
+msgid "Required for libatb.so, enables advanced tensor operations"
+msgstr "libatb.so 所需，支持高级张量运算"
+
+#: ../../source/quick_start.md:42
+msgid ""
+"Atlas 300I DUO uses CANN 9.1.0 and `float16`. Use the `-310p` image suffix "
+"for Ubuntu or `-310p-openeuler` for openEuler. Atlas 300I DUO does not "
+"support `triton` or `triton-ascend`."
+msgstr ""
+"Atlas 300I DUO 使用 CANN 9.1.0 和 `float16`。对于 Ubuntu 使用 `-310p` 镜像后缀，对于 "
+"openEuler 使用 `-310p-openeuler`。Atlas 300I DUO 不支持 `triton` 或 `triton-"
+"ascend`。"
+
+#: ../../source/quick_start.md:44
+#, python-brace-format
+msgid ""
+"Atlas 300I DUO and Atlas 200I Pro do not support `enable_npugraph_ex`. Set "
+"--additional-config '{\"ascend_compilation_config\": "
+"{\"enable_npugraph_ex\":false}}'."
+msgstr ""
+"Atlas 300I DUO 和 Atlas 200I Pro 不支持 `enable_npugraph_ex`。请设置 --additional-"
+"config '{\"ascend_compilation_config\": {\"enable_npugraph_ex\":false}}'。"
+
+#: ../../source/quick_start.md:46
+msgid ""
+"Atlas 200I Pro requires additional device nodes and driver mounts. See [Set "
+"up using Docker](installation.md#set-up-using-docker) for the complete "
+"container commands."
+msgstr ""
+"Atlas 200I Pro需要额外的设备节点和驱动挂载。完整的容器命令请参见[使用Docker设置](installation.md#set-up-"
+"using-docker)。"
+
+#: ../../source/quick_start.md:53
+msgid "triton / triton-ascend"
+msgstr "triton / triton-ascend"
+
+#: ../../source/quick_start.md:53
+msgid "Not supported"
+msgstr "不支持"
+
+#: ../../source/quick_start.md:53
+msgid "Uninstalled in `Dockerfile.310p`"
+msgstr "在 `Dockerfile.310p` 中未安装"
+
+#: ../../source/quick_start.md:65
 msgid "Setup environment using container"
-msgstr "使用容器设置环境"
+msgstr "使用容器搭建环境"

-#: ../../quick_start.md
+#: ../../source/quick_start.md:67
+msgid ""
+"Before using containers, make sure Docker is installed on your system. If "
+"Docker is not installed, please refer to the [Docker installation "
+"guide](https://docs.docker.com/get-started/get-docker/) for installation "
+"instructions."
+msgstr ""
+"在使用容器之前，请确保您的系统已安装 Docker。如果尚未安装 Docker，请参阅 [Docker "
+"安装指南](https://docs.docker.com/get-started/get-docker/) 获取安装说明。"
+
+#: ../../source/quick_start.md
 msgid "Ubuntu"
 msgstr "Ubuntu"

-#: ../../quick_start.md
+#: ../../source/quick_start.md
+msgid "Ubuntu (Atlas 300I DUO)"
+msgstr "Ubuntu (Atlas 300I DUO)"
+
+#: ../../source/quick_start.md:109 ../../source/quick_start.md:177
+msgid ""
+"The following command applies to Atlas 300I DUO. For Atlas 200I Pro, use the"
+" additional device nodes and driver mounts documented in "
+"[Installation](installation.md#set-up-using-docker)."
+msgstr ""
+"以下命令适用于 Atlas 300I DUO。对于 Atlas 200I Pro，请使用 [安装](installation.md#set-up-"
+"using-docker) 中记录的额外设备节点和驱动挂载。"
+
+#: ../../source/quick_start.md
 msgid "openEuler"
 msgstr "openEuler"

-#: ../../quick_start.md:69
+#: ../../source/quick_start.md
+msgid "openEuler (Atlas 300I DUO)"
+msgstr "openEuler (Atlas 300I DUO)"
+
+#: ../../source/quick_start.md:207
 msgid ""
-"The default workdir is `/workspace`, vLLM and vLLM Ascend code are placed "
-"in `/vllm-workspace` and installed in [development mode](https://setuptools."
-"pypa.io/en/latest/userguide/development_mode.html)(`pip install -e`) to "
-"help developer immediately take place changes without requiring a new "
-"installation."
+"The default workdir is `/workspace`, vLLM and vLLM Ascend code are placed in"
+" `/vllm-workspace` and installed in [development "
+"mode](https://setuptools.pypa.io/en/latest/userguide/development_mode.html) "
+"(`pip install -e`) to help developers make changes effective immediately "
+"without requiring a new installation."
 msgstr ""
-"默认的工作目录是 `/workspace`，vLLM 和 vLLM Ascend 代码被放置在 `/vllm-"
-"workspace`，并以[开发模式](https://setuptools.pypa.io/en/latest/userguide/"
-"development_mode.html)（`pip install -e`）安装，以便开发者能够即时生效更改，"
-"而无需重新安装。"
+"默认工作目录为`/workspace`，vLLM和vLLM Ascend代码位于`/vllm-"
+"workspace`，并以[开发模式](https://setuptools.pypa.io/en/latest/userguide/development_mode.html)（`pip"
+" install -e`）安装，帮助开发者即时生效更改，无需重新安装。"

-#: ../../quick_start.md:71
+#: ../../source/quick_start.md:209
 msgid "Usage"
-msgstr "用法"
+msgstr "使用方法"

-#: ../../quick_start.md:73
-msgid "You can use Modelscope mirror to speed up download:"
-msgstr "你可以使用 Modelscope 镜像来加速下载："
+#: ../../source/quick_start.md:211
+msgid "You can use ModelScope mirror to speed up download:"
+msgstr "您可以使用ModelScope镜像加速下载："

-#: ../../quick_start.md:80
+#: ../../source/quick_start.md:219
 msgid "There are two ways to start vLLM on Ascend NPU:"
-msgstr "在昇腾 NPU 上启动 vLLM 有两种方式："
+msgstr "在昇腾NPU上启动vLLM有两种方式："

-#: ../../quick_start.md
+#: ../../source/quick_start.md
 msgid "Offline Batched Inference"
 msgstr "离线批量推理"

-#: ../../quick_start.md:86
+#: ../../source/quick_start.md:225
 msgid ""
 "With vLLM installed, you can start generating texts for list of input "
-"prompts (i.e. offline batch inferencing)."
-msgstr ""
-"安装了 vLLM 后，您可以开始为一系列输入提示生成文本（即离线批量推理）。"
+"prompts (i.e. offline batch inference)."
+msgstr "安装vLLM后，您可以开始为输入提示列表生成文本（即离线批量推理）。"

-#: ../../quick_start.md:88
+#: ../../source/quick_start.md:227
+msgid "Create and run a simple inference test. The `example.py` can be like:"
+msgstr "创建并运行一个简单的推理测试。`example.py`可以如下所示："
+
+#: ../../source/quick_start.md:249
+msgid "Then run:"
+msgstr "然后运行："
+
+#: ../../source/quick_start.md:255
 msgid ""
-"Try to run below Python script directly or use `python3` shell to generate "
-"texts:"
+"If you encounter a connection error with Hugging Face (e.g., `We couldn't "
+"connect to 'https://huggingface.co' to load the files, and couldn't find "
+"them in the cached files.`), run the following commands to use ModelScope as"
+" an alternative:"
 msgstr ""
-"尝试直接运行下面的 Python 脚本，或者使用 `python3` 交互式命令行来生成文本："
+"如果遇到与Hugging Face的连接错误（例如`We couldn't connect to 'https://huggingface.co' to"
+" load the files, and couldn't find them in the cached "
+"files.`），请运行以下命令使用ModelScope作为替代："

-#: ../../quick_start.md
+#: ../../source/quick_start.md:263
+msgid "This section shows ascend platform is successfully detected in vllm:"
+msgstr "此部分显示vllm中成功检测到昇腾平台："
+
+#: ../../source/quick_start.md:272
+msgid "This section shows the final output:"
+msgstr "此部分显示最终输出："
+
+#: ../../source/quick_start.md:281
+msgid ""
+"This section shows process exits after offline inference, and does not "
+"affect actual inference:"
+msgstr "此部分显示进程在离线推理后退出，不影响实际推理："
+
+#: ../../source/quick_start.md
 msgid "OpenAI Completions API"
 msgstr "OpenAI Completions API"

-#: ../../quick_start.md:114
+#: ../../source/quick_start.md:294
 msgid ""
 "vLLM can also be deployed as a server that implements the OpenAI API "
-"protocol. Run the following command to start the vLLM server with the [Qwen/"
-"Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) "
-"model:"
+"protocol. Run the following command to start the vLLM server with the "
+"[Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) model:"
 msgstr ""
-"vLLM 也可以作为实现 OpenAI API 协议的服务器进行部署。运行以下命令，使用 "
-"[Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-"
-"Instruct) 模型启动 vLLM 服务器："
+"vLLM也可以部署为实现OpenAI "
+"API协议的服务器。运行以下命令，使用[Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)模型启动vLLM服务器："

-#: ../../quick_start.md:124
-msgid "If you see log as below:"
-msgstr "如果你看到如下日志："
+#: ../../source/quick_start.md:305
+msgid "If you see a log as below:"
+msgstr "如果您看到如下日志："

-#: ../../quick_start.md:132
+#: ../../source/quick_start.md:314
 msgid "Congratulations, you have successfully started the vLLM server!"
-msgstr "恭喜，你已经成功启动了 vLLM 服务器！"
+msgstr "恭喜，您已成功启动vLLM服务器！"

-#: ../../quick_start.md:134
-msgid "You can query the list the models:"
-msgstr "你可以查询模型列表："
+#: ../../source/quick_start.md:316
+msgid "You can query the list of models:"
+msgstr "您可以查询模型列表："

-#: ../../quick_start.md:141
+#: ../../source/quick_start.md:324
 msgid "You can also query the model with input prompts:"
-msgstr "你也可以通过输入提示来查询模型："
+msgstr "您也可以使用输入提示查询模型："

-#: ../../quick_start.md:155
+#: ../../source/quick_start.md:339
 msgid ""
-"vLLM is serving as background process, you can use `kill -2 $VLLM_PID` to "
-"stop the background process gracefully, it's equal to `Ctrl-C` to stop "
-"foreground vLLM process:"
+"vLLM is serving as a background process, you can use `kill -2 $VLLM_PID` to "
+"stop the background process gracefully, which is similar to `Ctrl-C` for "
+"stopping the foreground vLLM process:"
 msgstr ""
-"vLLM 正作为后台进程运行，你可以使用 `kill -2 $VLLM_PID` 来优雅地停止后台进"
-"程，这等同于使用 `Ctrl-C` 停止前台 vLLM 进程："
+"vLLM作为后台进程运行，您可以使用`kill -2 $VLLM_PID`优雅地停止后台进程，类似于使用`Ctrl-C`停止前台vLLM进程："

-#: ../../quick_start.md:164
-msgid "You will see output as below:"
-msgstr "你将会看到如下输出："
+#: ../../source/quick_start.md:348
+msgid "The output is as below:"
+msgstr "输出如下："

-#: ../../quick_start.md:172
-msgid "Finally, you can exit container by using `ctrl-D`."
-msgstr "最后，你可以通过按 `ctrl-D` 退出容器。"
+#: ../../source/quick_start.md:357
+msgid "Finally, you can exit the container by using `ctrl-D`."
+msgstr "最后，您可以使用`ctrl-D`退出容器。"
+
+#~ msgid "Atlas inference products"
+#~ msgstr "Atlas推理产品"
+
+#~ msgid ""
+#~ "Refer to the documentation [CANN "
+#~ "9.0.1](https://www.hiascend.com/document/detail/zh/canncommercial/900/releasenote/releasenote_0000.html)"
+#~ msgstr ""
+#~ "请参阅文档 [CANN "
+#~ "9.0.1](https://www.hiascend.com/document/detail/zh/canncommercial/900/releasenote/releasenote_0000.html)"
+
+#~ msgid "== 9.0.1"
+#~ msgstr "== 9.0.1"