提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00
parent deab7dd0b6
commit 7c22d621fb
175 changed files with 31856 additions and 8683 deletions
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/index.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/index.po
@@ -0,0 +1,177 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/contribution/index.md:1
+msgid "Contributing"
+msgstr "贡献"
+
+#: ../../source/developer_guide/contribution/index.md:3
+#, fuzzy
+msgid "Building and Testing"
+msgstr "构建与测试"
+
+#~ msgid "Index"
+#~ msgstr "索引"
+
+#~ msgid ""
+#~ "It's recommended to set up a local"
+#~ " development environment to build and "
+#~ "test before you submit a PR."
+#~ msgstr "建议先搭建本地开发环境来进行构建和测试，再提交 PR。"
+
+#~ msgid "Setup development environment"
+#~ msgstr "搭建开发环境"
+
+#~ msgid ""
+#~ "Theoretically, the vllm-kunlun build is"
+#~ " only supported on Linux because "
+#~ "`vllm-kunlun` dependency `torch_npu` only "
+#~ "supports Linux."
+#~ msgstr ""
+#~ "理论上，vllm-kunlun 构建仅支持 Linux，因为 `vllm-"
+#~ "kunlun` 的依赖项 `torch_npu` 只支持 Linux。"
+
+#~ msgid ""
+#~ "But you can still set up dev "
+#~ "env on Linux/Windows/macOS for linting "
+#~ "and basic test as following commands:"
+#~ msgstr "但你仍然可以在 Linux/Windows/macOS 上按照以下命令设置开发环境，用于代码规约检查和基本测试："
+
+#~ msgid "Run lint locally"
+#~ msgstr "在本地运行 lint"
+
+#~ msgid "Run CI locally"
+#~ msgstr "本地运行CI"
+
+#~ msgid "After complete \"Run lint\" setup, you can run CI locally:"
+#~ msgstr "在完成“运行 lint”设置后，你可以在本地运行 CI："
+
+#~ msgid "Submit the commit"
+#~ msgstr "提交该提交"
+
+#~ msgid ""
+#~ "🎉 Congratulations! You have completed "
+#~ "the development environment setup."
+#~ msgstr "🎉 恭喜！你已经完成了开发环境的搭建。"
+
+#~ msgid "Test locally"
+#~ msgstr "本地测试"
+
+#~ msgid ""
+#~ "You can refer to [Testing](./testing.md) "
+#~ "doc to help you setup testing "
+#~ "environment and running tests locally."
+#~ msgstr "你可以参考 [测试](./testing.md) 文档，帮助你搭建测试环境并在本地运行测试。"
+
+#~ msgid "DCO and Signed-off-by"
+#~ msgstr "DCO 和签名确认"
+
+#~ msgid ""
+#~ "When contributing changes to this "
+#~ "project, you must agree to the "
+#~ "DCO. Commits must include a `Signed-"
+#~ "off-by:` header which certifies "
+#~ "agreement with the terms of the "
+#~ "DCO."
+#~ msgstr "当为本项目贡献更改时，您必须同意 DCO。提交必须包含 `Signed-off-by:` 头部，以证明您同意 DCO 的条款。"
+
+#~ msgid "Using `-s` with `git commit` will automatically add this header."
+#~ msgstr "在使用 `git commit` 时加上 `-s` 参数会自动添加这个头部信息。"
+
+#~ msgid "PR Title and Classification"
+#~ msgstr "PR 标题与分类"
+
+#~ msgid ""
+#~ "Only specific types of PRs will be"
+#~ " reviewed. The PR title is prefixed"
+#~ " appropriately to indicate the type "
+#~ "of change. Please use one of the"
+#~ " following:"
+#~ msgstr "只有特定类型的 PR 会被审核。PR 标题应使用合适的前缀以指明更改类型。请使用以下之一："
+
+#~ msgid "`[Attention]` for new features or optimization in attention."
+#~ msgstr "`[Attention]` 用于注意力机制中新特性或优化。"
+
+#~ msgid "`[Communicator]` for new features or optimization in communicators."
+#~ msgstr "`[Communicator]` 适用于通信器中的新特性或优化。"
+
+#~ msgid "`[ModelRunner]` for new features or optimization in model runner."
+#~ msgstr "`[ModelRunner]` 用于模型运行器中的新功能或优化。"
+
+#~ msgid "`[Platform]` for new features or optimization in platform."
+#~ msgstr "`[Platform]` 用于平台中新功能或优化。"
+
+#~ msgid "`[Worker]` for new features or optimization in worker."
+#~ msgstr "`[Worker]` 用于 worker 的新功能或优化。"
+
+#~ msgid ""
+#~ "`[Core]` for new features or "
+#~ "optimization  in the core vllm-kunlun"
+#~ " logic (such as platform, attention, "
+#~ "communicators, model runner)"
+#~ msgstr "`[Core]` 用于核心 vllm-kunlun 逻辑中的新特性或优化（例如平台、注意力机制、通信器、模型运行器）。"
+
+#~ msgid "`[Kernel]` changes affecting compute kernels and ops."
+#~ msgstr "`[Kernel]` 影响计算内核和操作的更改。"
+
+#~ msgid "`[Bugfix]` for bug fixes."
+#~ msgstr "`[Bugfix]` 用于表示错误修复。"
+
+#~ msgid "`[Doc]` for documentation fixes and improvements."
+#~ msgstr "`[Doc]` 用于文档修复和改进。"
+
+#~ msgid "`[Test]` for tests (such as unit tests)."
+#~ msgstr "`[Test]` 用于测试（如单元测试）。"
+
+#~ msgid "`[CI]` for build or continuous integration improvements."
+#~ msgstr "`[CI]` 用于构建或持续集成的改进。"
+
+#~ msgid ""
+#~ "`[Misc]` for PRs that do not fit"
+#~ " the above categories. Please use "
+#~ "this sparingly."
+#~ msgstr "对于不属于上述类别的 PR，请使用 `[Misc]`。请谨慎使用此标签。"
+
+#~ msgid ""
+#~ "If the PR spans more than one "
+#~ "category, please include all relevant "
+#~ "prefixes."
+#~ msgstr "如果拉取请求（PR）涵盖多个类别，请包含所有相关的前缀。"
+
+#~ msgid "Others"
+#~ msgstr "其他"
+
+#~ msgid ""
+#~ "You may find more information about "
+#~ "contributing to vLLM Kunlun backend "
+#~ "plugin on "
+#~ "[<u>docs.vllm.ai</u>](https://docs.vllm.ai/en/latest/contributing/overview.html)."
+#~ " If you find any problem when "
+#~ "contributing, you can feel free to "
+#~ "submit a PR to improve the doc "
+#~ "to help other developers."
+#~ msgstr ""
+#~ "你可以在 "
+#~ "[<u>docs.vllm.ai</u>](https://docs.vllm.ai/en/latest/contributing/overview.html)"
+#~ " 上找到有关为 vLLM Kunlun "
+#~ "后端插件做贡献的更多信息。如果你在贡献过程中遇到任何问题，欢迎随时提交 PR 来改进文档，以帮助其他开发者。"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/multi_node_test.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/multi_node_test.po
@@ -0,0 +1,133 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:1
+msgid "Multi Node Test"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:3
+msgid ""
+"Multi-Node CI is designed to test distributed scenarios of very large "
+"models, eg: disaggregated_prefill multi DP across multi nodes and so on."
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:5
+msgid "How is works"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:7
+msgid ""
+"The following picture shows the basic deployment view of the multi-node "
+"CI mechanism, It shows how the github action interact with "
+"[lws](https://lws.sigs.k8s.io/docs/overview/) (a kind of kubernetes crd "
+"resource)"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:9
+msgid "![alt text](../../assets/deployment.png)"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:9
+#: ../../source/developer_guide/contribution/multi_node_test.md:13
+msgid "alt text"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:11
+msgid ""
+"From the workflow perspective, we can see how the final test script is "
+"executed, The key point is that these two [lws.yaml and "
+"run.sh](https://github.com/vllm-project/vllm-"
+"kunlun/tree/main/tests/e2e/nightly/multi_node/scripts), The former "
+"defines how our k8s cluster is pulled up, and the latter defines the "
+"entry script when the pod is started, Each node executes different logic "
+"according to the "
+"[LWS_WORKER_INDEX](https://lws.sigs.k8s.io/docs/reference/labels-"
+"annotations-and-environment-variables/) environment variable, so that "
+"multiple nodes can form a distributed cluster to perform tasks."
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:13
+msgid "![alt text](../../assets/workflow.png)"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:15
+msgid "How to contribute"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:17
+msgid "Upload custom weights"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:19
+msgid ""
+"If you need customized weights, for example, you quantized a w8a8 weight "
+"for DeepSeek-V3 and you want your weight to run on CI, Uploading weights "
+"to ModelScope's [vllm-kunlun](https://www.modelscope.cn/organization"
+"/vllm-kunlun) organization is welcome, If you do not have permission to "
+"upload, please contact @Potabk"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:21
+msgid "Add config yaml"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:23
+msgid ""
+"As the entrypoint script [run.sh](https://github.com/vllm-project/vllm-"
+"kunlun/blob/0bf3f21a987aede366ec4629ad0ffec8e32fe90d/tests/e2e/nightly/multi_node/scripts/run.sh#L106)"
+" shows, A k8s pod startup means traversing all *.yaml files in the "
+"[directory](https://github.com/vllm-project/vllm-"
+"kunlun/tree/main/tests/e2e/nightly/multi_node/config/models), reading and"
+" executing according to different configurations, so what we need to do "
+"is just add \"yamls\" like [DeepSeek-V3.yaml](https://github.com/vllm-"
+"project/vllm-"
+"kunlun/blob/main/tests/e2e/nightly/multi_node/config/models/DeepSeek-V3.yaml)."
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:25
+msgid ""
+"Suppose you have **2 nodes** running a 1P1D setup (1 Prefillers + 1 "
+"Decoder):"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:27
+msgid "you may add a config file looks like:"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:69
+msgid ""
+"Add the case to nightly workflow currently, the multi-node test workflow "
+"defined in the [vllm_kunlun_test_nightly_a2/a3.yaml](https://github.com"
+"/vllm-project/vllm-"
+"kunlun/blob/main/.github/workflows/vllm_kunlun_test_nightly_a3.yaml)"
+msgstr ""
+
+#: ../../source/developer_guide/contribution/multi_node_test.md:99
+msgid ""
+"The matrix above defines all the parameters required to add a multi-"
+"machine use case, The parameters worth paying attention to (I mean if you"
+" are adding a new use case) are size and the path to the yaml "
+"configuration file. The former defines the number of nodes required for "
+"your use case, and the latter defines the path to the configuration file "
+"you have completed in step 2."
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po
@@ -0,0 +1,265 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/contribution/testing.md:1
+msgid "Testing"
+msgstr "测试"
+
+#: ../../source/developer_guide/contribution/testing.md:3
+#, fuzzy
+msgid ""
+"This document explains how to write E2E tests and unit tests to verify "
+"the implementation of your feature."
+msgstr "本节介绍如何编写端到端测试和单元测试，以验证你的功能实现。"
+
+#: ../../source/developer_guide/contribution/testing.md:5
+#, fuzzy
+msgid "Setup a test environment"
+msgstr "设置测试环境"
+
+#: ../../source/developer_guide/contribution/testing.md:7
+#, fuzzy
+msgid ""
+"The fastest way to setup a test environment is to use the main branch's "
+"container image:"
+msgstr "搭建测试环境最快的方法是使用 main 分支的容器镜像："
+
+#: ../../source/developer_guide/contribution/testing.md
+msgid "Local (CPU)"
+msgstr "本地（CPU）"
+
+#: ../../source/developer_guide/contribution/testing.md:18
+#, fuzzy
+msgid "You can run the unit tests on CPUs with the following steps:"
+msgstr "你可以按照以下步骤在 CPU 上运行单元测试："
+
+#: ../../source/developer_guide/contribution/testing.md
+msgid "Single card"
+msgstr "单张卡片"
+
+#: ../../source/developer_guide/contribution/testing.md:86
+#: ../../source/developer_guide/contribution/testing.md:125
+msgid "After starting the container, you should install the required packages:"
+msgstr "启动容器后，你应该安装所需的软件包："
+
+#: ../../source/developer_guide/contribution/testing.md
+msgid "Multi cards"
+msgstr "多卡"
+
+#: ../../source/developer_guide/contribution/testing.md:139
+msgid "Running tests"
+msgstr "运行测试"
+
+#: ../../source/developer_guide/contribution/testing.md:141
+#, fuzzy
+msgid "Unit tests"
+msgstr "单元测试"
+
+#: ../../source/developer_guide/contribution/testing.md:143
+msgid "There are several principles to follow when writing unit tests:"
+msgstr "编写单元测试时需要遵循几个原则："
+
+#: ../../source/developer_guide/contribution/testing.md:145
+#, fuzzy
+msgid ""
+"The test file path should be consistent with the source file and start "
+"with the `test_` prefix, such as: `vllm_kunlun/worker/worker_v1.py` --> "
+"`tests/ut/worker/test_worker_v1.py`"
+msgstr ""
+"测试文件的路径应与源文件保持一致，并以 `test_` 前缀开头，例如：`vllm_kunlun/worker/worker_v1.py` -->"
+" `tests/ut/worker/test_worker_v1.py`"
+
+#: ../../source/developer_guide/contribution/testing.md:146
+#, fuzzy
+msgid ""
+"The vLLM Kunlun test uses unittest framework. See "
+"[here](https://docs.python.org/3/library/unittest.html#module-unittest) "
+"to understand how to write unit tests."
+msgstr ""
+"vLLM Kunlun 测试使用 unittest "
+"框架，参见[这里](https://docs.python.org/3/library/unittest.html#module-"
+"unittest)了解如何编写单元测试。"
+
+#: ../../source/developer_guide/contribution/testing.md:147
+#, fuzzy
+msgid ""
+"All unit tests can be run on CPUs, so you must mock the device-related "
+"function to host."
+msgstr "所有单元测试都可以在 CPU 上运行，因此你必须将与设备相关的函数模拟为 host。"
+
+#: ../../source/developer_guide/contribution/testing.md:148
+msgid ""
+"Example: [tests/ut/test_kunlun_config.py](https://github.com/vllm-project"
+"/vllm-kunlun/blob/main/tests/ut/test_kunlun_config.py)."
+msgstr ""
+"示例：[tests/ut/test_kunlun_config.py](https://github.com/vllm-project/vllm-"
+"kunlun/blob/main/tests/ut/test_kunlun_config.py)。"
+
+#: ../../source/developer_guide/contribution/testing.md:149
+msgid "You can run the unit tests using `pytest`:"
+msgstr "你可以使用 `pytest` 运行单元测试："
+
+#: ../../source/developer_guide/contribution/testing.md
+#, fuzzy
+msgid "Single-card"
+msgstr "单张卡片"
+
+#: ../../source/developer_guide/contribution/testing.md
+#, fuzzy
+msgid "Multi-card"
+msgstr "多卡"
+
+#: ../../source/developer_guide/contribution/testing.md:196
+msgid "E2E test"
+msgstr "端到端测试"
+
+#: ../../source/developer_guide/contribution/testing.md:198
+#, fuzzy
+msgid ""
+"Although vllm-kunlun CI provides the [E2E test](https://github.com/vllm-"
+"project/vllm-kunlun/blob/main/.github/workflows/vllm_kunlun_test.yaml) on"
+" Kunlun CI, you can run it locally."
+msgstr ""
+"虽然 vllm-kunlun CI 在 Kunlun CI 上提供了 [端到端测试](https://github.com/vllm-"
+"project/vllm-"
+"kunlun/blob/main/.github/workflows/vllm_kunlun_test.yaml)，你也可以在本地运行它。"
+
+#: ../../source/developer_guide/contribution/testing.md:208
+#, fuzzy
+msgid "You can't run the E2E test on CPUs."
+msgstr "你无法在 CPU 上运行 e2e 测试。"
+
+#: ../../source/developer_guide/contribution/testing.md:247
+#, fuzzy
+msgid ""
+"This will reproduce the E2E test. See "
+"[vllm_kunlun_test.yaml](https://github.com/vllm-project/vllm-"
+"kunlun/blob/main/.github/workflows/vllm_kunlun_test.yaml)."
+msgstr ""
+"这将复现端到端测试：[vllm_kunlun_test.yaml](https://github.com/vllm-project/vllm-"
+"kunlun/blob/main/.github/workflows/vllm_kunlun_test.yaml)。"
+
+#: ../../source/developer_guide/contribution/testing.md:249
+msgid "E2E test example:"
+msgstr "E2E 测试示例："
+
+#: ../../source/developer_guide/contribution/testing.md:251
+msgid ""
+"Offline test example: "
+"[`tests/e2e/singlecard/test_offline_inference.py`](https://github.com"
+"/vllm-project/vllm-"
+"kunlun/blob/main/tests/e2e/singlecard/test_offline_inference.py)"
+msgstr ""
+"离线测试示例：[`tests/e2e/singlecard/test_offline_inference.py`](https://github.com"
+"/vllm-project/vllm-"
+"kunlun/blob/main/tests/e2e/singlecard/test_offline_inference.py)"
+
+#: ../../source/developer_guide/contribution/testing.md:252
+msgid ""
+"Online test examples: "
+"[`tests/e2e/singlecard/test_prompt_embedding.py`](https://github.com"
+"/vllm-project/vllm-"
+"kunlun/blob/main/tests/e2e/singlecard/test_prompt_embedding.py)"
+msgstr ""
+"在线测试示例：[`tests/e2e/singlecard/test_prompt_embedding.py`](https://github.com"
+"/vllm-project/vllm-"
+"kunlun/blob/main/tests/e2e/singlecard/test_prompt_embedding.py)"
+
+#: ../../source/developer_guide/contribution/testing.md:253
+msgid ""
+"Correctness test example: "
+"[`tests/e2e/singlecard/test_aclgraph.py`](https://github.com/vllm-project"
+"/vllm-kunlun/blob/main/tests/e2e/singlecard/test_aclgraph.py)"
+msgstr ""
+"正确性测试示例：[`tests/e2e/singlecard/test_aclgraph.py`](https://github.com"
+"/vllm-project/vllm-"
+"kunlun/blob/main/tests/e2e/singlecard/test_aclgraph.py)"
+
+#: ../../source/developer_guide/contribution/testing.md:254
+msgid ""
+"Reduced Layer model test example: [test_torchair_graph_mode.py - "
+"DeepSeek-V3-Pruning](https://github.com/vllm-project/vllm-"
+"kunlun/blob/20767a043cccb3764214930d4695e53941de87ec/tests/e2e/multicard/test_torchair_graph_mode.py#L48)"
+msgstr ""
+"简化层模型测试示例：[test_torchair_graph_mode.py - "
+"DeepSeek-V3-Pruning](https://github.com/vllm-project/vllm-"
+"kunlun/blob/20767a043cccb3764214930d4695e53941de87ec/tests/e2e/multicard/test_torchair_graph_mode.py#L48)"
+
+#: ../../source/developer_guide/contribution/testing.md:256
+#, fuzzy
+msgid ""
+"The CI resource is limited, and you might need to reduce the number of "
+"layers of a model. Below is an example of how to generate a reduced layer"
+" model:"
+msgstr "CI 资源有限，您可能需要减少模型的层数，下面是一个生成减少层数模型的示例："
+
+#: ../../source/developer_guide/contribution/testing.md:257
+#, fuzzy
+msgid ""
+"Fork the original model repo in modelscope. All the files in the repo "
+"except for weights are required."
+msgstr "在 modelscope 中 fork 原始模型仓库，我们需要仓库中的所有文件，除了权重文件。"
+
+#: ../../source/developer_guide/contribution/testing.md:258
+#, python-brace-format
+msgid ""
+"Set `num_hidden_layers` to the expected number of layers, e.g., "
+"`{\"num_hidden_layers\": 2,}`"
+msgstr "将 `num_hidden_layers` 设置为期望的层数，例如 `{\"num_hidden_layers\": 2,}`"
+
+#: ../../source/developer_guide/contribution/testing.md:259
+msgid ""
+"Copy the following python script as `generate_random_weight.py`. Set the "
+"relevant parameters `MODEL_LOCAL_PATH`, `DIST_DTYPE` and "
+"`DIST_MODEL_PATH` as needed:"
+msgstr ""
+"将以下 Python 脚本复制为 `generate_random_weight.py`。根据需要设置相关参数 "
+"`MODEL_LOCAL_PATH`、`DIST_DTYPE` 和 `DIST_MODEL_PATH`："
+
+#: ../../source/developer_guide/contribution/testing.md:277
+msgid "Run doctest"
+msgstr "运行 doctest"
+
+#: ../../source/developer_guide/contribution/testing.md:279
+#, fuzzy
+msgid ""
+"vllm-kunlun provides a `vllm-kunlun/tests/e2e/run_doctests.sh` command to"
+" run all doctests in the doc files. The doctest is a good way to make "
+"sure docs stay current and examples remain executable, which can be run "
+"locally as follows:"
+msgstr ""
+"vllm-kunlun 提供了一个 `vllm-kunlun/tests/e2e/run_doctests.sh` 命令，用于运行文档文件中的所有"
+" doctest。doctest 是确保文档保持最新且示例可执行的好方法，你可以按照以下方式在本地运行它："
+
+#: ../../source/developer_guide/contribution/testing.md:287
+#, fuzzy
+msgid ""
+"This will reproduce the same environment as the CI. See "
+"[vllm_kunlun_doctest.yaml](https://github.com/vllm-project/vllm-"
+"kunlun/blob/main/.github/workflows/vllm_kunlun_doctest.yaml)."
+msgstr ""
+"这将复现与 CI 相同的环境：[vllm_kunlun_doctest.yaml](https://github.com/vllm-project"
+"/vllm-kunlun/blob/main/.github/workflows/vllm_kunlun_doctest.yaml)。"
+
+#~ msgid "Multi cards test"
+#~ msgstr "多卡测试"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/DeepSeek-V2-Lite.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/DeepSeek-V2-Lite.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/accuracy_report/DeepSeek-V2-Lite.md:1
+msgid "deepseek-ai/DeepSeek-V2-Lite"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/Qwen2.5-VL-7B-Instruct.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/Qwen2.5-VL-7B-Instruct.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/accuracy_report/Qwen2.5-VL-7B-Instruct.md:1
+msgid "Qwen/Qwen2.5-VL-7B-Instruct"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/Qwen3-30B-A3B.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/Qwen3-30B-A3B.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/accuracy_report/Qwen3-30B-A3B.md:1
+msgid "Qwen/Qwen3-30B-A3B"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/Qwen3-8B-Base.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/Qwen3-8B-Base.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/accuracy_report/Qwen3-8B-Base.md:1
+msgid "Qwen/Qwen3-8B-Base"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/index.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/index.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/evaluation/accuracy_report/index.md:1
+#: ../../developer_guide/evaluation/accuracy_report/index.md:3
+msgid "Accuracy Report"
+msgstr "准确性报告"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/index.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/index.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/evaluation/index.md:1
+#: ../../developer_guide/evaluation/index.md:3
+msgid "Accuracy"
+msgstr "准确性"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_ais_bench.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_ais_bench.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/using_ais_bench.md:1
+msgid "Using AISBench"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_evalscope.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_evalscope.po
@@ -0,0 +1,100 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/using_evalscope.md:1
+msgid "Using EvalScope"
+msgstr "使用 EvalScope"
+
+#~ msgid ""
+#~ "This document will guide you have "
+#~ "model inference stress testing and "
+#~ "accuracy testing using "
+#~ "[EvalScope](https://github.com/modelscope/evalscope)."
+#~ msgstr ""
+#~ "本文档将指导您如何使用 [EvalScope](https://github.com/modelscope/evalscope)"
+#~ " 进行模型推理压力测试和精度测试。"
+
+#~ msgid "1. Online serving"
+#~ msgstr "1. 在线服务"
+
+#~ msgid "You can run docker container to start the vLLM server on a single XPU:"
+#~ msgstr "你可以运行 docker 容器，在单个 XPU 上启动 vLLM 服务器："
+
+#~ msgid "If your service start successfully, you can see the info shown below:"
+#~ msgstr "如果你的服务启动成功，你会看到如下所示的信息："
+
+#~ msgid ""
+#~ "Once your server is started, you "
+#~ "can query the model with input "
+#~ "prompts in new terminal:"
+#~ msgstr "一旦你的服务器启动后，你可以在新的终端中用输入提示词查询模型："
+
+#~ msgid "2. Install EvalScope using pip"
+#~ msgstr "2. 使用 pip 安装 EvalScope"
+
+#~ msgid "You can install EvalScope by using:"
+#~ msgstr "你可以使用以下方式安装 EvalScope："
+
+#~ msgid "3. Run gsm8k accuracy test using EvalScope"
+#~ msgstr "3. 使用 EvalScope 运行 gsm8k 准确率测试"
+
+#~ msgid "You can `evalscope eval` run gsm8k accuracy test:"
+#~ msgstr "你可以使用 `evalscope eval` 运行 gsm8k 准确率测试："
+
+#~ msgid "After 1-2 mins, the output is as shown below:"
+#~ msgstr "1-2 分钟后，输出如下所示："
+
+#~ msgid ""
+#~ "See more detail in: [EvalScope doc "
+#~ "- Model API Service "
+#~ "Evaluation](https://evalscope.readthedocs.io/en/latest/get_started/basic_usage.html"
+#~ "#model-api-service-evaluation)."
+#~ msgstr ""
+#~ "更多详情请见：[EvalScope 文档 - 模型 API "
+#~ "服务评测](https://evalscope.readthedocs.io/en/latest/get_started/basic_usage.html"
+#~ "#model-api-service-evaluation)。"
+
+#~ msgid "4. Run model inference stress testing using EvalScope"
+#~ msgstr "4. 使用 EvalScope 运行模型推理压力测试"
+
+#~ msgid "Install EvalScope[perf] using pip"
+#~ msgstr "使用 pip 安装 EvalScope[perf]"
+
+#~ msgid "Basic usage"
+#~ msgstr "基本用法"
+
+#~ msgid "You can use `evalscope perf` run perf test:"
+#~ msgstr "你可以使用 `evalscope perf` 运行性能测试："
+
+#~ msgid "Output results"
+#~ msgstr "输出结果"
+
+#~ msgid ""
+#~ "See more detail in: [EvalScope doc "
+#~ "- Model Inference Stress "
+#~ "Testing](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test/quick_start.html"
+#~ "#basic-usage)."
+#~ msgstr ""
+#~ "更多详情见：[EvalScope 文档 - "
+#~ "模型推理压力测试](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test/quick_start.html"
+#~ "#basic-usage)。"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po
@@ -0,0 +1,62 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/using_lm_eval.md:1
+msgid "Using lm-eval"
+msgstr "使用 lm-eval"
+
+#~ msgid ""
+#~ "This document will guide you have "
+#~ "a accuracy testing using [lm-"
+#~ "eval](https://github.com/EleutherAI/lm-evaluation-"
+#~ "harness)."
+#~ msgstr ""
+#~ "本文将指导你如何使用 [lm-eval](https://github.com/EleutherAI/lm-"
+#~ "evaluation-harness) 进行准确率测试。"
+
+#~ msgid "1. Run docker container"
+#~ msgstr "1. 运行 docker 容器"
+
+#~ msgid "You can run docker container on a single XPU:"
+#~ msgstr "你可以在单个XPU上运行docker容器："
+
+#~ msgid "2. Run ceval accuracy test using lm-eval"
+#~ msgstr "2. 使用 lm-eval 运行 ceval 准确性测试"
+
+#~ msgid "Install lm-eval in the container."
+#~ msgstr "在容器中安装 lm-eval。"
+
+#~ msgid "Run the following command:"
+#~ msgstr "运行以下命令："
+
+#~ msgid "After 1-2 mins, the output is as shown below:"
+#~ msgstr "1-2 分钟后，输出如下所示："
+
+#~ msgid ""
+#~ "You can see more usage on [Lm-"
+#~ "eval Docs](https://github.com/EleutherAI/lm-evaluation-"
+#~ "harness/blob/main/docs/README.md)."
+#~ msgstr ""
+#~ "你可以在 [Lm-eval 文档](https://github.com/EleutherAI"
+#~ "/lm-evaluation-harness/blob/main/docs/README.md) "
+#~ "上查看更多用法。"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_opencompass.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_opencompass.po
@@ -0,0 +1,77 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/evaluation/using_opencompass.md:1
+msgid "Using OpenCompass"
+msgstr "使用 OpenCompass"
+
+#~ msgid ""
+#~ "This document will guide you have "
+#~ "a accuracy testing using "
+#~ "[OpenCompass](https://github.com/open-compass/opencompass)."
+#~ msgstr ""
+#~ "本文档将指导你如何使用 [OpenCompass](https://github.com/open-"
+#~ "compass/opencompass) 进行准确率测试。"
+
+#~ msgid "1. Online Serving"
+#~ msgstr "1. 在线服务"
+
+#~ msgid "You can run docker container to start the vLLM server on a single XPU:"
+#~ msgstr "你可以运行 docker 容器，在单个 XPU 上启动 vLLM 服务器："
+
+#~ msgid "If your service start successfully, you can see the info shown below:"
+#~ msgstr "如果你的服务启动成功，你会看到如下所示的信息："
+
+#~ msgid ""
+#~ "Once your server is started, you "
+#~ "can query the model with input "
+#~ "prompts in new terminal:"
+#~ msgstr "一旦你的服务器启动后，你可以在新的终端中用输入提示词查询模型："
+
+#~ msgid "2. Run ceval accuracy test using OpenCompass"
+#~ msgstr "2. 使用 OpenCompass 运行 ceval 准确率测试"
+
+#~ msgid ""
+#~ "Install OpenCompass and configure the "
+#~ "environment variables in the container."
+#~ msgstr "在容器中安装 OpenCompass 并配置环境变量。"
+
+#~ msgid ""
+#~ "Add `opencompass/configs/eval_vllm_kunlun_demo.py` with"
+#~ " the following content:"
+#~ msgstr "添加 `opencompass/configs/eval_vllm_kunlun_demo.py`，内容如下："
+
+#~ msgid "Run the following command:"
+#~ msgstr "运行以下命令："
+
+#~ msgid "After 1-2 mins, the output is as shown below:"
+#~ msgstr "1-2 分钟后，输出如下所示："
+
+#~ msgid ""
+#~ "You can see more usage on "
+#~ "[OpenCompass "
+#~ "Docs](https://opencompass.readthedocs.io/en/latest/index.html)."
+#~ msgstr ""
+#~ "你可以在 [OpenCompass "
+#~ "文档](https://opencompass.readthedocs.io/en/latest/index.html) "
+#~ "查看更多用法。"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/ACL_Graph.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/ACL_Graph.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/feature_guide/ACL_Graph.md:1
+msgid "Graph"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/KV_Cache_Pool_Guide.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/KV_Cache_Pool_Guide.po
@@ -0,0 +1,30 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/feature_guide/KV_Cache_Pool_Guide.md:1
+msgid "KV Cache Pool"
+msgstr ""
+
+#: ../../source/developer_guide/feature_guide/KV_Cache_Pool_Guide.md:3
+msgid "Why KV Cache Pool?"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/ModelRunner_prepare_inputs.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/ModelRunner_prepare_inputs.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/feature_guide/ModelRunner_prepare_inputs.md:1
+msgid "Prepare inputs for model forwarding"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/Multi_Token_Prediction.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/Multi_Token_Prediction.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/feature_guide/Multi_Token_Prediction.md:1
+msgid "Multi Token Prediction (MTP)"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/eplb_swift_balancer.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/eplb_swift_balancer.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/feature_guide/eplb_swift_balancer.md:1
+msgid "Expert Parallelism Load Balancer (EPLB)"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/index.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/index.po
@@ -0,0 +1,33 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/feature_guide/index.md:1
+#: ../../developer_guide/feature_guide/index.md:5
+msgid "Feature Guide"
+msgstr "功能指南"
+
+#: ../../developer_guide/feature_guide/index.md:3
+msgid ""
+"This section provides an overview of the features implemented in vLLM "
+"Kunlun. Developers can refer to this guide to understand how vLLM Kunlun "
+"works."
+msgstr "本节概述了 vLLM Kunlun 中实现的功能。开发者可以参考本指南以了解 vLLM Kunlun 的工作原理。"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/patch.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/patch.po
@@ -0,0 +1,288 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/feature_guide/patch.md:1
+#, fuzzy
+msgid "Patch in vLLM"
+msgstr "在 vLLM Kunlun 中的补丁"
+
+#~ msgid ""
+#~ "vLLM Kunlun is a platform plugin "
+#~ "for vLLM. Due to the release cycle"
+#~ " of vLLM and vLLM Kunlun is "
+#~ "different, and the hardware limitation "
+#~ "in some case, we need to patch "
+#~ "some code in vLLM to make it "
+#~ "compatible with vLLM Kunlun."
+#~ msgstr ""
+#~ "vLLM Kunlun 是 vLLM 的一个平台插件。由于 vLLM "
+#~ "和 vLLM Kunlun 的发布周期不同，并且在某些情况下存在硬件限制，我们需要对 "
+#~ "vLLM 进行一些代码补丁，以使其能够兼容 vLLM Kunlun。"
+
+#~ msgid ""
+#~ "In vLLM Kunlun code, we provide a"
+#~ " patch module `vllm_kunlun/patch` to "
+#~ "address the change for vLLM."
+#~ msgstr "在 vLLM Kunlun 代码中，我们提供了一个补丁模块 `vllm_kunlun/patch` 用于应对 vLLM 的变更。"
+
+#~ msgid "Principle"
+#~ msgstr "原理"
+
+#~ msgid ""
+#~ "We should keep in mind that Patch"
+#~ " is not the best way to make"
+#~ " vLLM Kunlun compatible. It's just a"
+#~ " temporary solution. The best way is"
+#~ " to contribute the change to vLLM "
+#~ "to make it compatible with vLLM "
+#~ "Kunlun originally. In vLLM Kunlun, we"
+#~ " have the basic principle for Patch"
+#~ " strategy:"
+#~ msgstr ""
+#~ "我们需要记住，Patch 不是让 vLLM 兼容 Kunlun "
+#~ "的最佳方式，这只是一个临时的解决方案。最好的方法是将修改贡献到 vLLM 项目中，从而让 vLLM"
+#~ " 原生支持 Kunlun。对于 vLLM Kunlun，我们对 Patch "
+#~ "策略有一个基本原则："
+
+#~ msgid "Less is more. Please do not patch unless it's the only way currently."
+#~ msgstr "少即是多。请不要打补丁，除非这是目前唯一的方法。"
+
+#~ msgid ""
+#~ "Once a patch is added, it's "
+#~ "required to describe the future plan "
+#~ "for removing the patch."
+#~ msgstr "一旦补丁被添加，必须说明将来移除该补丁的计划。"
+
+#~ msgid "Anytime, clean the patch code is welcome."
+#~ msgstr "任何时候，欢迎清理补丁代码。"
+
+#~ msgid "How it works"
+#~ msgstr "工作原理"
+
+#~ msgid "In `vllm_kunlun/patch`, you can see the code structure as follows:"
+#~ msgstr "在 `vllm_kunlun/patch` 目录中，你可以看到如下代码结构："
+
+#~ msgid ""
+#~ "**platform**: The patch code in this "
+#~ "directory is for patching the code "
+#~ "in vLLM main process. It's called "
+#~ "by `vllm_kunlun/platform::XPUPlatform::pre_register_and_update`"
+#~ " very early when vLLM is initialized."
+#~ msgstr ""
+#~ "**platform**：此目录下的补丁代码用于修补 vLLM 主进程中的代码。当 vLLM "
+#~ "初始化时，会在很早的阶段由 "
+#~ "`vllm_kunlun/platform::XPUPlatform::pre_register_and_update` 调用。"
+
+#~ msgid ""
+#~ "For online mode, vLLM process calls "
+#~ "the platform patch here "
+#~ "`vllm/vllm/engine/arg_utils.py::AsyncEngineArgs.add_cli_args` "
+#~ "when parsing the cli args."
+#~ msgstr ""
+#~ "对于在线模式，vLLM 进程在解析命令行参数时，会在 "
+#~ "`vllm/vllm/engine/arg_utils.py::AsyncEngineArgs.add_cli_args` "
+#~ "这里调用平台补丁。"
+
+#~ msgid ""
+#~ "For offline mode, vLLM process calls "
+#~ "the platform patch here "
+#~ "`vllm/vllm/engine/arg_utils.py::EngineArgs.create_engine_config` "
+#~ "when parsing the input parameters."
+#~ msgstr ""
+#~ "对于离线模式，vLLM 进程在解析输入参数时，会在此处调用平台补丁 "
+#~ "`vllm/vllm/engine/arg_utils.py::EngineArgs.create_engine_config`。"
+
+#~ msgid ""
+#~ "**worker**: The patch code in this "
+#~ "directory is for patching the code "
+#~ "in vLLM worker process. It's called "
+#~ "by `vllm_kunlun/worker/worker_v1::XPUWorker::__init__` "
+#~ "when the vLLM worker process is "
+#~ "initialized."
+#~ msgstr ""
+#~ "**worker**：此目录中的补丁代码用于修补 vLLM worker 进程中的代码。在初始化 "
+#~ "vLLM worker 进程时，会被 "
+#~ "`vllm_kunlun/worker/worker_v1::XPUWorker::__init__` 调用。"
+
+#~ msgid ""
+#~ "For both online and offline mode, "
+#~ "vLLM engine core process calls the "
+#~ "worker patch here "
+#~ "`vllm/vllm/worker/worker_base.py::WorkerWrapperBase.init_worker` "
+#~ "when initializing the worker process."
+#~ msgstr ""
+#~ "无论是在线还是离线模式，vLLM 引擎核心进程在初始化 worker 进程时，都会在这里调用 "
+#~ "worker "
+#~ "补丁：`vllm/vllm/worker/worker_base.py::WorkerWrapperBase.init_worker`。"
+
+#~ msgid ""
+#~ "In both **platform** and **worker** "
+#~ "folder, there are several patch modules."
+#~ " They are used for patching different"
+#~ " version of vLLM."
+#~ msgstr "在 **platform** 和 **worker** 文件夹中都有一些补丁模块。它们用于修补不同版本的 vLLM。"
+
+#~ msgid ""
+#~ "`patch_0_9_2`: This module is used for"
+#~ " patching vLLM 0.9.2. The version is"
+#~ " always the nearest version of vLLM."
+#~ " Once vLLM is released, we will "
+#~ "drop this patch module and bump to"
+#~ " a new version. For example, "
+#~ "`patch_0_9_2` is used for patching vLLM"
+#~ " 0.9.2."
+#~ msgstr ""
+#~ "`patch_0_9_2`：此模块用于修补 vLLM 0.9.2。该版本始终对应于 vLLM "
+#~ "的最近版本。一旦 vLLM 发布新版本，我们将移除此补丁模块并升级到新版本。例如，`patch_0_9_2` "
+#~ "就是用于修补 vLLM 0.9.2 的。"
+
+#~ msgid ""
+#~ "`patch_main`: This module is used for"
+#~ " patching the code in vLLM main "
+#~ "branch."
+#~ msgstr "`patch_main`：该模块用于修补 vLLM 主分支代码。"
+
+#~ msgid ""
+#~ "`patch_common`: This module is used for"
+#~ " patching both vLLM 0.9.2 and vLLM"
+#~ " main branch."
+#~ msgstr "`patch_common`：此模块用于同时修补 vLLM 0.9.2 版本和 vLLM 主分支。"
+
+#~ msgid "How to write a patch"
+#~ msgstr "如何撰写补丁"
+
+#~ msgid ""
+#~ "Before writing a patch, following the"
+#~ " principle above, we should patch the"
+#~ " least code. If it's necessary, we"
+#~ " can patch the code in either "
+#~ "**platform** and **worker** folder. Here "
+#~ "is an example to patch `distributed` "
+#~ "module in vLLM."
+#~ msgstr ""
+#~ "在编写补丁之前，遵循上述原则，我们应尽量修改最少的代码。如果有必要，我们可以修改 **platform** 和"
+#~ " **worker** 文件夹中的代码。下面是一个在 vLLM 中修改 "
+#~ "`distributed` 模块的示例。"
+
+#~ msgid ""
+#~ "Decide which version of vLLM we "
+#~ "should patch. For example, after "
+#~ "analysis, here we want to patch "
+#~ "both 0.9.2 and main of vLLM."
+#~ msgstr "决定我们应该修补哪个版本的 vLLM。例如，经过分析后，这里我们想要同时修补 vLLM 的 0.9.2 版和主分支（main）。"
+
+#~ msgid ""
+#~ "Decide which process we should patch."
+#~ " For example, here `distributed` belongs"
+#~ " to the vLLM main process, so "
+#~ "we should patch `platform`."
+#~ msgstr "决定我们应该修补哪个进程。例如，这里 `distributed` 属于 vLLM 主进程，所以我们应该修补 `platform`。"
+
+#~ msgid ""
+#~ "Create the patch file in the right"
+#~ " folder. The file should be named "
+#~ "as `patch_{module_name}.py`. The example here"
+#~ " is "
+#~ "`vllm_kunlun/patch/platform/patch_common/patch_distributed.py`."
+#~ msgstr ""
+#~ "在正确的文件夹中创建补丁文件。文件应命名为 `patch_{module_name}.py`。此处的示例是 "
+#~ "`vllm_kunlun/patch/platform/patch_common/patch_distributed.py`。"
+
+#~ msgid "Write your patch code in the new file. Here is an example:"
+#~ msgstr "在新文件中编写你的补丁代码。以下是一个示例："
+
+#~ msgid ""
+#~ "Import the patch file in `__init__.py`."
+#~ " In this example, add `import "
+#~ "vllm_kunlun.patch.platform.patch_common.patch_distributed` into"
+#~ " `vllm_kunlun/patch/platform/patch_common/__init__.py`."
+#~ msgstr ""
+#~ "在 `__init__.py` 中导入补丁文件。在这个示例中，将 `import "
+#~ "vllm_kunlun.patch.platform.patch_common.patch_distributed` 添加到"
+#~ " `vllm_kunlun/patch/platform/patch_common/__init__.py` 中。"
+
+#~ msgid ""
+#~ "Add the description of the patch "
+#~ "in `vllm_kunlun/patch/__init__.py`. The description"
+#~ " format is as follows:"
+#~ msgstr "在 `vllm_kunlun/patch/__init__.py` 中添加补丁的描述。描述格式如下："
+
+#~ msgid ""
+#~ "Add the Unit Test and E2E Test."
+#~ " Any newly added code in vLLM "
+#~ "Kunlun should contain the Unit Test "
+#~ "and E2E Test as well. You can "
+#~ "find more details in [test "
+#~ "guide](../contribution/testing.md)"
+#~ msgstr ""
+#~ "添加单元测试和端到端（E2E）测试。在 vLLM Kunlun "
+#~ "中新增的任何代码也应包含单元测试和端到端测试。更多详情请参见 "
+#~ "[测试指南](../contribution/testing.md)。"
+
+#~ msgid "Limitation"
+#~ msgstr "限制"
+
+#~ msgid ""
+#~ "In V1 Engine, vLLM starts three "
+#~ "kinds of process: Main process, "
+#~ "EngineCore process and Worker process. "
+#~ "Now vLLM Kunlun only support patch "
+#~ "the code in Main process and "
+#~ "Worker process by default. If you "
+#~ "want to patch the code runs in "
+#~ "EngineCore process, you should patch "
+#~ "EngineCore process entirely during setup, "
+#~ "the entry code is here "
+#~ "`vllm.v1.engine.core`. Please override "
+#~ "`EngineCoreProc` and `DPEngineCoreProc` entirely."
+#~ msgstr ""
+#~ "在 V1 引擎中，vLLM 会启动三种类型的进程：主进程、EngineCore 进程和"
+#~ " Worker 进程。现在 vLLM Kunlun 默认只支持在主进程和 "
+#~ "Worker 进程中打补丁代码。如果你想要在 EngineCore 进程中打补丁，你需要在设置阶段对"
+#~ " EngineCore 进程整体打补丁，入口代码在 `vllm.v1.engine.core`。请完全重写"
+#~ " `EngineCoreProc` 和 `DPEngineCoreProc`。"
+
+#~ msgid ""
+#~ "If you are running an edited vLLM"
+#~ " code, the version of the vLLM "
+#~ "may be changed automatically. For "
+#~ "example, if you runs an edited "
+#~ "vLLM based on v0.9.n, the version "
+#~ "of vLLM may be change to "
+#~ "v0.9.nxxx, in this case, the patch "
+#~ "for v0.9.n in vLLM Kunlun would "
+#~ "not work as expect, because that "
+#~ "vLLM Kunlun can't distinguish the "
+#~ "version of vLLM you're using. In "
+#~ "this case, you can set the "
+#~ "environment variable `VLLM_VERSION` to specify"
+#~ " the version of vLLM you're using,"
+#~ " then the patch for v0.9.2 should "
+#~ "work."
+#~ msgstr ""
+#~ "如果你运行的是经过编辑的 vLLM 代码，vLLM 的版本可能会被自动更改。例如，如果你基于 "
+#~ "v0.9.n 运行了编辑后的 vLLM，vLLM 的版本可能会变为 "
+#~ "v0.9.nxxx，在这种情况下，vLLM Kunlun 的 v0.9.n "
+#~ "补丁将无法正常工作，因为 vLLM Kunlun 无法区分你所使用的 vLLM "
+#~ "版本。这时，你可以设置环境变量 `VLLM_VERSION` 来指定你所使用的 vLLM "
+#~ "版本，这样对 v0.9.2 的补丁就应该可以正常工作。"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_model.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_model.po
@@ -0,0 +1,333 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:1
+msgid "Adding a New Model"
+msgstr "添加新模型"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:3
+msgid ""
+"This guide demonstrates how to integrate a novel or customized model into "
+"vllm-kunlun. For foundational concepts, it is highly recommended to refer to"
+" [vllm official doc: Adding a New "
+"Model](https://docs.vllm.ai/en/stable/contributing/model/) first."
+msgstr ""
+"本指南演示如何将新颖或自定义的模型集成到 vllm-kunlun 中。对于基础概念，强烈建议先参考 [vllm "
+"官方文档：添加新模型](https://docs.vllm.ai/en/stable/contributing/model/)。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:6
+msgid "Step 1: Implementing Models with `torch` and `torch_npu`"
+msgstr "步骤 1：使用 `torch` 和 `torch_npu` 实现模型"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:8
+msgid ""
+"This section provides instructions for implementing new models compatible "
+"with vllm and vllm-kunlun."
+msgstr "本节提供了实现与 vllm 和 vllm-kunlun 兼容的新模型的相关说明。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:10
+msgid "**Before starting:**"
+msgstr "**开始之前：**"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:12
+msgid ""
+"Verify whether your model already exists in vllm's "
+"[models](https://github.com/vllm-"
+"project/vllm/tree/main/vllm/model_executor/models) directory."
+msgstr ""
+"请确认你的模型是否已经存在于 vllm 的 [models](https://github.com/vllm-"
+"project/vllm/tree/main/vllm/model_executor/models) 目录中。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:13
+msgid ""
+"Use existing models' implementation as templates to accelerate your "
+"development."
+msgstr "使用已有模型的实现作为模板以加速您的开发。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:15
+msgid "Method 1: Implementing New Models from Scratch"
+msgstr "方法一：从零开始实现新模型"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:17
+msgid ""
+"Follow vllm's [OPT model "
+"adaptation](https://docs.vllm.ai/en/stable/contributing/model/basic.html) "
+"example for guidance."
+msgstr ""
+"请参考 vllm 的 [OPT "
+"模型适配](https://docs.vllm.ai/en/stable/contributing/model/basic.html) 示例进行操作。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:19
+msgid "**Key implementation requirements:**"
+msgstr "**关键实现要求：**"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:21
+msgid "Place model files in `vllm_kunlun/models/` directory."
+msgstr "请将模型文件放在 `vllm_kunlun/models/` 目录下。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:23
+msgid ""
+"Standard module structure for decoder-only LLMs (please checkout vllm's "
+"implementations for other kinds of model):"
+msgstr "解码器-only LLMs 的标准模块结构（请参考 vllm 对其他类型模型的实现）："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:25
+msgid "`*ModelForCausalLM` (top-level wrapper)"
+msgstr "`*ModelForCausalLM`（顶层包装器）"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:26
+msgid "`*Model` (main architecture)"
+msgstr "`*Model`（主架构）"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:27
+msgid "`*DecoderLayer` (transformer block)"
+msgstr "`*DecoderLayer` （transformer 块）"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:28
+msgid "`*Attention` and `*MLP` (specific computation unit)"
+msgstr "`*Attention` 和 `*MLP`（特定计算单元）"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:31
+msgid "`*` denotes your model's unique identifier."
+msgstr "`*` 表示你的模型的唯一标识符。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:34
+msgid "Critical Implementation Details:"
+msgstr "关键实现细节："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:36
+msgid "All modules must include a `prefix` argument in `__init__()`."
+msgstr "所有模块在 `__init__()` 方法中都必须包含一个 `prefix` 参数。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:38
+msgid "**Required interfaces:**"
+msgstr "**必需的接口：**"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:30
+msgid "Module Type"
+msgstr "模块类型"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:30
+msgid "Required Methods"
+msgstr "必需的方法"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:30
+msgid "`*ModelForCausalLM`"
+msgstr "`*ModelForCausalLM`"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:30
+msgid "`get_input_embeddings`, `compute_logits`, `load_weights`"
+msgstr "`get_input_embeddings`，`compute_logits`，`load_weights`"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:30
+msgid "`*Model`"
+msgstr "`*模型`"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:30
+msgid "`get_input_embeddings`, `load_weights`"
+msgstr "`get_input_embeddings`，`load_weights`"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:45
+msgid "Attention Backend Integration:"
+msgstr "注意后端集成："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:47
+msgid ""
+"Importing attention via `from vllm.attention import Attention` can "
+"automatically leverage the attention backend routing of vllm-kunlun (see: "
+"`get_attn_backend_cls()` in `vllm_kunlun/platform.py`)."
+msgstr ""
+"通过 `from vllm.attention import Attention` 导入 attention 可以自动利用 vllm-kunlun "
+"的注意力后端路由（详见：`vllm_kunlun/platform.py` 中的 `get_attn_backend_cls()`）。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:49
+msgid "Tensor Parallelism:"
+msgstr "张量并行："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:51
+msgid ""
+"Use vllm's parallel layers (`ColumnParallelLinear`, "
+"`VocabParallelEmbedding`, etc.) to implement models supporting tensor "
+"parallelism. Note that Kunlun-specific customizations are implemented in "
+"`vllm_kunlun/ops/` directory (RMSNorm, VocabParallelEmbedding, etc.)."
+msgstr ""
+"使用 vllm 的并行层（如 `ColumnParallelLinear`、`VocabParallelEmbedding` "
+"等）来实现支持张量并行的模型。需要注意的是，Kunlun 特有的自定义实现（如 RMSNorm、VocabParallelEmbedding 等）位于 "
+"`vllm_kunlun/ops/` 目录下。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:53
+msgid ""
+"**Reference Implementation Template** (assumed path: "
+"`vllm_kunlun/models/custom_model.py`):"
+msgstr "**参考实现模板**（假定路径：`vllm_kunlun/models/custom_model.py`）："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:135
+msgid "Method 2: Customizing Existing vLLM Models"
+msgstr "方法二：自定义已有的 vLLM 模型"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:137
+msgid ""
+"For most use cases, extending existing implementations is preferable. We "
+"demonstrate an example to inherit from base classes and implement a custom "
+"deepseek model below (assumed path: `vllm_kunlun/models/deepseek_v2.py`)."
+msgstr ""
+"对于大多数使用场景，建议扩展已有的实现。我们在下面演示了一个示例，通过继承基类并实现一个自定义的 deepseek "
+"模型（假定路径：`vllm_kunlun/models/deepseek_v2.py`）。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:175
+msgid ""
+"For a complete implementation reference, see: "
+"`vllm_kunlun/models/deepseek_v2.py`."
+msgstr "完整的实现参考请见：`vllm_kunlun/models/deepseek_v2.py`。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:178
+msgid "Step 2: Registering Custom Models using ModelRegistry Plugins in vLLM"
+msgstr "第2步：使用 vLLM 中的 ModelRegistry 插件注册自定义模型"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:180
+msgid ""
+"vllm provides a plugin mechanism for registering externally implemented "
+"models without modifying its codebase."
+msgstr "vllm 提供了一种插件机制，可用于注册外部实现的模型，而无需修改其代码库。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:182
+msgid ""
+"To integrate your implemented model from `vllm_kunlun/models/` directory:"
+msgstr "要集成你在 `vllm_kunlun/models/` 目录下实现的模型："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:184
+msgid ""
+"Import your model implementation in `vllm_kunlun/models/__init__.py` using "
+"relative imports."
+msgstr "使用相对导入在 `vllm_kunlun/models/__init__.py` 中导入你的模型实现。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:185
+msgid ""
+"Register the model wrapper class via `vllm.ModelRegistry.register_model()` "
+"function."
+msgstr "通过 `vllm.ModelRegistry.register_model()` 函数注册模型包装类。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:187
+msgid ""
+"**Reference Registration Template** (an example of registering new models in"
+" `vllm_kunlun/models/__init__.py`):"
+msgstr "**参考注册模板**（在 `vllm_kunlun/models/__init__.py` 注册新模型的示例）："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:210
+msgid ""
+"The first argument of `vllm.ModelRegistry.register_model()` indicates the "
+"unique architecture identifier which must match `architectures` in "
+"`config.json` of the model."
+msgstr ""
+"`vllm.ModelRegistry.register_model()` 的第一个参数表示唯一的架构标识符，这个标识符必须与模型的 "
+"`config.json` 文件中的 `architectures` 匹配。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:221
+msgid "Step 3: Verification"
+msgstr "第 3 步：验证"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:223
+msgid "Case 1: Overriding Existing vLLM Model Architecture"
+msgstr "案例 1：重载已有的 vLLM 模型架构"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:225
+msgid ""
+"If you're registering a customized model architecture based on vllm's "
+"existing implementation (overriding vllm's original class), when executing "
+"vllm offline/online inference (using any model), you'll observe warning logs"
+" similar to the following output from "
+"`vllm/models_executor/models/registry.py`."
+msgstr ""
+"如果你基于 vllm 的现有实现注册了一个自定义的模型架构（覆盖了 vllm 的原始类），在执行 vllm "
+"的离线/在线推理（无论使用哪个模型）时，你会看到类似于 `vllm/models_executor/models/registry.py` "
+"输出的警告日志。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:231
+msgid "Case 2: Registering New Model Architecture"
+msgstr "案例2：注册新模型架构"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:233
+msgid ""
+"If you're registering a novel model architecture not present in vllm "
+"(creating a completely new class), current logs won't provide explicit "
+"confirmation by default. It's recommended to add the following logging "
+"statement at the end of the `register_model` method in "
+"`vllm/models_executor/models/registry.py`."
+msgstr ""
+"如果你注册了 vllm 中不存在的新模型架构（创建一个全新的类），当前日志默认不会提供明确的确认信息。建议在 "
+"`vllm/models_executor/models/registry.py` 文件中的 `register_model` "
+"方法末尾添加如下日志语句。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:239
+msgid ""
+"After adding this line, you will see confirmation logs shown below when "
+"running vllm offline/online inference (using any model)."
+msgstr "添加这一行之后，当你运行 vllm 离线/在线推理（使用任何模型）时，将会看到如下确认日志。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:245
+msgid ""
+"This log output confirms your novel model architecture has been successfully"
+" registered in vllm."
+msgstr "该日志输出确认了你的新模型架构已成功在 vllm 中注册。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:247
+msgid "Step 4: Testing"
+msgstr "第4步：测试"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:249
+msgid ""
+"After adding a new model, we should do basic functional test (offline/online"
+" inference), accuracy test and performance benchmark for the model."
+msgstr "在添加新模型后，我们应对该模型进行基本功能测试（离线/在线推理）、准确率测试和性能基准测试。"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:251
+msgid "Find more details at:"
+msgstr "更多详情请见："
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:253
+msgid ""
+"[Accuracy test guide](https://vllm-"
+"kunlun.readthedocs.io/en/latest/developer_guide/evaluation/index.html)"
+msgstr ""
+"[精度测试指南](https://vllm-"
+"kunlun.readthedocs.io/en/latest/developer_guide/evaluation/index.html)"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:254
+msgid ""
+"[Performance benchmark guide](https://vllm-"
+"kunlun.readthedocs.io/en/latest/developer_guide/performance/performance_benchmark.html)"
+msgstr ""
+"[性能基准指南](https://vllm-"
+"kunlun.readthedocs.io/en/latest/developer_guide/performance/performance_benchmark.html)"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:256
+msgid "Step 5: Updating Supported Models Doc"
+msgstr "第5步：更新支持的模型文档"
+
+#: ../../developer_guide/modeling/adding_a_new_model.md:258
+msgid ""
+"At last, if all the steps above are completed, you should add the new model "
+"into our [Supported Models](https://vllm-"
+"kunlun.readthedocs.io/en/latest/user_guide/supported_models.html) doc."
+msgstr ""
+"最后，如果以上所有步骤都已完成，你应该将新模型添加到我们的[支持的模型](https://vllm-"
+"kunlun.readthedocs.io/en/latest/user_guide/supported_models.html)文档中。"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_multimodal_model.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_multimodal_model.po
@@ -0,0 +1,29 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/modeling/adding_a_new_multimodal_model.md:1
+msgid "Adding a New Multi-Modal Model"
+msgstr "添加新的多模态模型"
+
+#: ../../developer_guide/modeling/adding_a_new_multimodal_model.md:3
+msgid "**_Comming soon ..._**"
+msgstr "**_敬请期待 ..._**"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/index.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/index.po
@@ -0,0 +1,32 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/modeling/index.md:1
+#: ../../developer_guide/modeling/index.md:5
+msgid "Modeling"
+msgstr "新模型"
+
+#: ../../developer_guide/modeling/index.md:3
+msgid ""
+"This section provides tutorials of how to implement and register a new model"
+" into vllm-kunlun."
+msgstr "本节提供了如何在 vllm-kunlun 中实现并注册新模型的教程。"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/index.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/index.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-07-18 09:01+0800\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"
+
+#: ../../developer_guide/performance/index.md:1
+#: ../../developer_guide/performance/index.md:3
+msgid "Performance"
+msgstr "性能"
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/optimization_and_tuning.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/optimization_and_tuning.po
@@ -0,0 +1,26 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: vllm-kunlun \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/performance/optimization_and_tuning.md:1
+msgid "Optimization and Tuning"
+msgstr ""
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/performance_benchmark.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/performance_benchmark.po
@@ -0,0 +1,92 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/performance/performance_benchmark.md:1
+msgid "Performance Benchmark"
+msgstr "性能基准"
+
+#~ msgid ""
+#~ "This document details the benchmark "
+#~ "methodology for vllm-kunlun, aimed at"
+#~ " evaluating the performance under a "
+#~ "variety of workloads. To maintain "
+#~ "alignment with vLLM, we use the "
+#~ "[benchmark](https://github.com/vllm-"
+#~ "project/vllm/tree/main/benchmarks) script provided "
+#~ "by the vllm project."
+#~ msgstr ""
+#~ "本文档详细说明了 vllm-kunlun 的基准测试方法，旨在评估其在多种工作负载下的性能。为了与"
+#~ " vLLM 保持一致，我们使用 vllm 项目提供的 "
+#~ "[benchmark](https://github.com/vllm-"
+#~ "project/vllm/tree/main/benchmarks) 脚本。"
+
+#~ msgid ""
+#~ "**Benchmark Coverage**: We measure offline "
+#~ "e2e latency and throughput, and "
+#~ "fixed-QPS online serving benchmarks, for"
+#~ " more details see [vllm-kunlun "
+#~ "benchmark scripts](https://github.com/vllm-project"
+#~ "/vllm-kunlun/tree/main/benchmarks)."
+#~ msgstr ""
+#~ "**基准测试覆盖范围**：我们测量离线端到端延迟和吞吐量，以及固定 QPS 的在线服务基准测试。更多详情请参见"
+#~ " [vllm-kunlun 基准测试脚本](https://github.com/vllm-"
+#~ "project/vllm-kunlun/tree/main/benchmarks)。"
+
+#~ msgid "1. Run docker container"
+#~ msgstr "1. 运行 docker 容器"
+
+#~ msgid "2. Install dependencies"
+#~ msgstr "2. 安装依赖项"
+
+#~ msgid "3. (Optional)Prepare model weights"
+#~ msgstr "3.（可选）准备模型权重"
+
+#~ msgid ""
+#~ "For faster running speed, we recommend"
+#~ " downloading the model in advance："
+#~ msgstr "为了更快的运行速度，建议提前下载模型："
+
+#~ msgid ""
+#~ "You can also replace all model "
+#~ "paths in the [json](https://github.com/vllm-"
+#~ "project/vllm-kunlun/tree/main/benchmarks/tests) files "
+#~ "with your local paths:"
+#~ msgstr ""
+#~ "你也可以将 [json](https://github.com/vllm-project/vllm-"
+#~ "kunlun/tree/main/benchmarks/tests) 文件中的所有模型路径替换为你的本地路径："
+
+#~ msgid "4. Run benchmark script"
+#~ msgstr "4. 运行基准测试脚本"
+
+#~ msgid "Run benchmark script:"
+#~ msgstr "运行基准测试脚本："
+
+#~ msgid "After about 10 mins, the output is as shown below:"
+#~ msgstr "大约 10 分钟后，输出如下所示："
+
+#~ msgid ""
+#~ "The result json files are generated "
+#~ "into the path `benchmark/results` These "
+#~ "files contain detailed benchmarking results"
+#~ " for further analysis."
+#~ msgstr "结果 json 文件会生成到路径 `benchmark/results`。这些文件包含了用于进一步分析的详细基准测试结果。"
+
--- a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/profile_execute_duration.po
+++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/profile_execute_duration.po
@@ -0,0 +1,86 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, vllm-kunlun team
+# This file is distributed under the same license as the vllm-kunlun
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version:  vllm-kunlun\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-11-10 16:59+0800\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language: zh_CN\n"
+"Language-Team: zh_CN <LL@li.org>\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.17.0\n"
+
+#: ../../source/developer_guide/performance/profile_execute_duration.md:1
+msgid "Profile Execute Duration"
+msgstr "配置执行持续时间"
+
+#~ msgid ""
+#~ "The execution duration of each stage "
+#~ "(including pre/post-processing, model forward,"
+#~ " etc.) usually needs to be captured"
+#~ " during a complete inference process. "
+#~ "Typically, this is done by using "
+#~ "`torch.xpu.synchronize()` and obtaining CPU "
+#~ "timestamps, which increases the performance"
+#~ " overhead of host/device synchronization."
+#~ msgstr ""
+#~ "在完整的推理过程中，通常需要记录每个阶段（包括前/后处理、模型前向等）的执行时长。一般通过使用 "
+#~ "`torch.xpu.synchronize()` 并获取 CPU "
+#~ "时间戳来实现，这会增加主机/设备同步的性能开销。"
+
+#~ msgid ""
+#~ "**To reduce the performance overhead, we"
+#~ " add this feature, using the XPU "
+#~ "event timestamp mechanism to observe the"
+#~ " device execution time asynchronously.**"
+#~ msgstr "**为了减少性能开销，我们添加了此功能，使用 XPU 事件时间戳机制异步观测设备的执行时间。**"
+
+#~ msgid "Usage"
+#~ msgstr "用法"
+
+#~ msgid ""
+#~ "Use the environment variable "
+#~ "`VLLM_KUNLUN_MODEL_EXECUTE_TIME_OBSERVE` to enable "
+#~ "this feature."
+#~ msgstr "使用环境变量 `VLLM_KUNLUN_MODEL_EXECUTE_TIME_OBSERVE` 来启用此功能。"
+
+#~ msgid ""
+#~ "Use the non-blocking API "
+#~ "`ProfileExecuteDuration().capture_async` to set "
+#~ "observation points asynchronously when you "
+#~ "need to observe the execution duration."
+#~ msgstr ""
+#~ "当你需要观察执行时长时，可以使用非阻塞 API "
+#~ "`ProfileExecuteDuration().capture_async` 异步设置观察点。"
+
+#~ msgid ""
+#~ "Use the blocking API "
+#~ "`ProfileExecuteDuration().pop_captured_sync` at an "
+#~ "appropriate time to get and print "
+#~ "the execution durations of all observed"
+#~ " stages."
+#~ msgstr ""
+#~ "在适当的时机使用阻塞式 API "
+#~ "`ProfileExecuteDuration().pop_captured_sync` 获取并打印所有已观察到阶段的执行时长。"
+
+#~ msgid ""
+#~ "**We have instrumented the key inference"
+#~ " stages (including pre-processing, model"
+#~ " forward pass, etc.) for execute "
+#~ "duration profiling. Execute the script "
+#~ "as follows:**"
+#~ msgstr "**我们已经对关键的推理阶段（包括预处理、模型前向传递等）进行了执行时长分析的检测。请按如下方式执行脚本：**"
+
+#~ msgid "Example Output"
+#~ msgstr "示例输出"
+