DOC: add release notes doc (#4157)

Author: qinxuye

doc/source/getting_started/index.rst

@@ -15,3 +15,4 @@ Getting Started
    using_kubernetes
    troubleshooting
    environments
+   release_notes

doc/source/getting_started/release_notes.rst

@@ -0,0 +1,21 @@
+.. _release_ntoes:
+
+Release Notes
+=============
+
+This page provides a version-by-version index of Xinference release notes.
+For detailed updates, please visit the corresponding links below.
+
++-----------------+--------------------------------------------------------------------------------+
+| Version         | Release Notes                                                                  |
++=================+================================================================================+
+| v1.11.0.post1   | `View release notes <https://xinference.io/release_notes/v1.11.0.post1.html>`_ |
++-----------------+--------------------------------------------------------------------------------+
+| v1.10.1         | `View release notes <https://xinference.io/release_notes/v1.10.1.html>`_       |
++-----------------+--------------------------------------------------------------------------------+
+
+----
+
+For older versions and source history, see our GitHub releases page:
+https://github.com/xorbitsai/inference/releases
+

doc/source/getting_started/using_xinference.rst

@@ -326,6 +326,9 @@ The following OpenAI APIs are supported:
 
 - Embeddings: `https://platform.openai.com/docs/api-reference/embeddings <https://platform.openai.com/docs/api-reference/embeddings>`_
 
+Xinference also supports Anthropic API via base url ``http://127.0.0.1:9997/anthropic``, you can use Xinference in Claude Code and so forth.
+Refer to :ref:`anthropic client <anthropic_client>` for more details.
+
 Manage Models
 -------------
 

doc/source/locale/zh_CN/LC_MESSAGES/getting_started/release_notes.po

@@ -0,0 +1,65 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2025, Xorbits Inc.
+# This file is distributed under the same license as the Xinference package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2025.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: Xinference \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2025-10-21 12:57+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 <[email protected]>\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 2.14.0\n"
+
+#: ../../source/getting_started/release_notes.rst:4
+#: ../../source/getting_started/release_notes.rst:10
+msgid "Release Notes"
+msgstr "版本发布说明"
+
+#: ../../source/getting_started/release_notes.rst:6
+msgid ""
+"This page provides a version-by-version index of Xinference release "
+"notes. For detailed updates, please visit the corresponding links below."
+msgstr ""
+"本页面提供 Xinference 各版本的发布说明索引。有关详细更新，请访问对应的链接。"
+
+#: ../../source/getting_started/release_notes.rst:10
+msgid "Version"
+msgstr "版本"
+
+#: ../../source/getting_started/release_notes.rst:12
+msgid "v1.11.0.post1"
+msgstr ""
+
+#: ../../source/getting_started/release_notes.rst:12
+msgid ""
+"`View release notes "
+"<https://xinference.io/release_notes/v1.11.0.post1.html>`_"
+msgstr ""
+"`查看版本说明 "
+"<https://xinference.cn/release_notes/v1.11.0.post1.html>`_"
+
+#: ../../source/getting_started/release_notes.rst:14
+msgid "v1.10.1"
+msgstr ""
+
+#: ../../source/getting_started/release_notes.rst:14
+msgid "`View release notes <https://xinference.io/release_notes/v1.10.1.html>`_"
+msgstr ""
+"`查看版本说明 "
+"<https://xinference.cn/release_notes/v1.10.1.html>`_"
+
+#: ../../source/getting_started/release_notes.rst:19
+msgid ""
+"For older versions and source history, see our GitHub releases page: "
+"https://github.com/xorbitsai/inference/releases"
+msgstr ""
+"更多历史版本及源代码，请访问 GitHub Releases：https://github.com/xorbitsai/inference/releases"

doc/source/locale/zh_CN/LC_MESSAGES/getting_started/using_xinference.po

@@ -6,7 +6,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Xinference \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-08-04 12:08+0800\n"
+"POT-Creation-Date: 2025-10-21 13:27+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -376,11 +376,21 @@ msgstr ""
 "向量生成：`https://platform.openai.com/docs/api-reference/embeddings <"
 "https://platform.openai.com/docs/api-reference/embeddings>`_"
 
-#: ../../source/getting_started/using_xinference.rst:330
+#: ../../source/getting_started/using_xinference.rst:329
+msgid ""
+"Xinference also supports Anthropic API via base url "
+"``http://127.0.0.1:9997/anthropic``, you can use Xinference in Claude "
+"Code and so forth. Refer to :ref:`anthropic client <anthropic_client>` "
+"for more details."
+msgstr ""
+"Xinference 还支持通过基础 URL ``http://127.0.0.1:9997/anthropic`` 调用 Anthropic API，"
+"你可以在 Claude Code 等环境中使用 Xinference。更多详情请参阅 :ref:`anthropic client <anthropic_client>`。"
+
+#: ../../source/getting_started/using_xinference.rst:333
 msgid "Manage Models"
 msgstr "管理模型"
 
-#: ../../source/getting_started/using_xinference.rst:332
+#: ../../source/getting_started/using_xinference.rst:335
 msgid ""
 "In addition to launching models, Xinference offers various ways to manage"
 " the entire lifecycle of models. You can manage models in Xinference "
@@ -389,37 +399,37 @@ msgstr ""
 "除了启动模型，Xinference 提供了管理模型整个生命周期的能力。同样的，你可以"
 "使用命令行、cURL 以及 Python 代码来管理："
 
-#: ../../source/getting_started/using_xinference.rst:335
+#: ../../source/getting_started/using_xinference.rst:338
 msgid ""
 "You can list all models of a certain type that are available to launch in"
 " Xinference:"
 msgstr "可以列出所有 Xinference 支持的指定类型的模型："
 
-#: ../../source/getting_started/using_xinference.rst:353
+#: ../../source/getting_started/using_xinference.rst:356
 msgid ""
 "The following command gives you the currently running models in "
 "Xinference:"
 msgstr "接下来的命令可以列出所有在运行的模型："
 
-#: ../../source/getting_started/using_xinference.rst:371
+#: ../../source/getting_started/using_xinference.rst:374
 msgid ""
 "When you no longer need a model that is currently running, you can remove"
 " it in the following way to free up the resources it occupies:"
 msgstr "当你不需要某个正在运行的模型，可以通过以下的方式来停止它并释放资源："
 
-#: ../../source/getting_started/using_xinference.rst:392
+#: ../../source/getting_started/using_xinference.rst:395
 msgid "Deploy Xinference In a Cluster"
 msgstr "集群中部署 Xinference"
 
-#: ../../source/getting_started/using_xinference.rst:394
+#: ../../source/getting_started/using_xinference.rst:397
 msgid ""
 "To deploy Xinference in a cluster, you need to start a Xinference "
 "supervisor on one server and Xinference workers on the other servers."
 msgstr ""
 "若要在集群环境中部署 Xinference，需要在一台机器中启动 supervisor 节点，并"
 "在当前或者其他节点启动 worker 节点"
 
-#: ../../source/getting_started/using_xinference.rst:397
+#: ../../source/getting_started/using_xinference.rst:400
 msgid ""
 "First, make sure you have already installed Xinference on each of the "
 "servers according to the instructions provided :ref:`here "
@@ -428,23 +438,23 @@ msgstr ""
 "首先，根据 :ref:`文档 <installation>` 确保所有的服务器上都安装了 "
 "Xinference。接下来按照步骤："
 
-#: ../../source/getting_started/using_xinference.rst:401
+#: ../../source/getting_started/using_xinference.rst:404
 msgid "Start the Supervisor"
 msgstr "启动 Supervisor"
 
-#: ../../source/getting_started/using_xinference.rst:402
+#: ../../source/getting_started/using_xinference.rst:405
 msgid ""
 "On the server where you want to run the Xinference supervisor, run the "
 "following command:"
 msgstr "在服务器上执行以下命令来启动 Supervisor 节点："
 
-#: ../../source/getting_started/using_xinference.rst:408
+#: ../../source/getting_started/using_xinference.rst:411
 msgid ""
 "Replace ``${supervisor_host}`` with the actual host of your supervisor "
 "server."
 msgstr "用当前节点的 IP 来替换 ``${supervisor_host}``。"
 
-#: ../../source/getting_started/using_xinference.rst:411
+#: ../../source/getting_started/using_xinference.rst:414
 msgid ""
 "You can the supervisor's web UI at `http://${supervisor_host}:9997/ui "
 "<http://${supervisor_host}:9997/ui>`_ and visit "
@@ -455,23 +465,23 @@ msgstr ""
 "/ui>`_ 访问 web UI，在 `http://${supervisor_host}:9997/docs <http://${"
 "supervisor_host}:9997/docs>`_ 访问 API 文档。"
 
-#: ../../source/getting_started/using_xinference.rst:415
+#: ../../source/getting_started/using_xinference.rst:418
 msgid "Start the Workers"
 msgstr "启动 Worker"
 
-#: ../../source/getting_started/using_xinference.rst:417
+#: ../../source/getting_started/using_xinference.rst:420
 msgid ""
 "On each of the other servers where you want to run Xinference workers, "
 "run the following command:"
 msgstr "在需要启动 Xinference worker 的机器上执行以下命令："
 
-#: ../../source/getting_started/using_xinference.rst:424
+#: ../../source/getting_started/using_xinference.rst:427
 msgid ""
 "Note that you must replace ``${worker_host}``  with the actual host of "
 "your worker server."
 msgstr "需要注意的是，必须使用当前Worker节点的 IP 来替换 ``${worker_host}``。"
 
-#: ../../source/getting_started/using_xinference.rst:427
+#: ../../source/getting_started/using_xinference.rst:430
 msgid ""
 "Note that if you need to interact with the Xinference in a cluster via "
 "the command line, you should include the ``-e`` or ``--endpoint`` flag to"
@@ -480,56 +490,55 @@ msgstr ""
 "需要注意的是，如果你需要通过命令行与集群交互，应该通过 ``-e`` 或者 ``--"
 "endpoint`` 参数来指定 supervisor 的地址，比如："
 
-#: ../../source/getting_started/using_xinference.rst:435
+#: ../../source/getting_started/using_xinference.rst:438
 msgid "Using Xinference With Docker"
 msgstr "使用 Docker 部署 Xinference"
 
-#: ../../source/getting_started/using_xinference.rst:437
+#: ../../source/getting_started/using_xinference.rst:440
 msgid "To start Xinference in a Docker container, run the following command:"
 msgstr "用以下命令在容器中运行 Xinference："
 
-#: ../../source/getting_started/using_xinference.rst:440
+#: ../../source/getting_started/using_xinference.rst:443
 msgid "Run On Nvidia GPU Host"
 msgstr "在拥有英伟达显卡的机器上运行"
 
-#: ../../source/getting_started/using_xinference.rst:442
+#: ../../source/getting_started/using_xinference.rst:445
 msgid "For cuda 12.4:"
 msgstr "对于 cuda 12.4："
 
-#: ../../source/getting_started/using_xinference.rst:448
+#: ../../source/getting_started/using_xinference.rst:451
 msgid "For cuda 12.8:"
 msgstr "对于 cuda 12.8："
 
-#: ../../source/getting_started/using_xinference.rst:450
+#: ../../source/getting_started/using_xinference.rst:453
 msgid ""
 "CUDA 12.8 version is experimental, welcome to give us feedbacks to help "
 "us to improve."
-msgstr ""
-"CUDA 12.8 版本是实验性质，欢迎给我们反馈以改进。"
+msgstr "CUDA 12.8 版本是实验性质，欢迎给我们反馈以改进。"
 
-#: ../../source/getting_started/using_xinference.rst:458
+#: ../../source/getting_started/using_xinference.rst:461
 msgid "Run On CPU Only Host"
 msgstr "在只有 CPU 的机器上运行"
 
-#: ../../source/getting_started/using_xinference.rst:464
+#: ../../source/getting_started/using_xinference.rst:467
 msgid ""
 "Replace ``<your_version>`` with Xinference versions, e.g. ``v0.10.3``, "
 "``latest`` can be used for the latest version."
 msgstr ""
 "将 ``<your_version>`` 替换为 Xinference 的版本，比如 ``v0.10.3``，可以用 "
 "``latest`` 来用于最新版本。"
 
-#: ../../source/getting_started/using_xinference.rst:466
+#: ../../source/getting_started/using_xinference.rst:469
 msgid ""
 "For more docker usage, refer to :ref:`Using Docker Image "
 "<using_docker_image>`."
 msgstr "更多 docker 使用，请参考 :ref:`使用 docker 镜像 <using_docker_image>`。"
 
-#: ../../source/getting_started/using_xinference.rst:470
+#: ../../source/getting_started/using_xinference.rst:473
 msgid "What's Next?"
 msgstr "更多"
 
-#: ../../source/getting_started/using_xinference.rst:472
+#: ../../source/getting_started/using_xinference.rst:475
 msgid ""
 "Congratulations on getting started with Xinference! To help you navigate "
 "and make the most out of this powerful tool, here are some resources and "
@@ -538,12 +547,12 @@ msgstr ""
 "恭喜你，已经初步掌握了 Xinference 的用法！为了帮助你更好地使用工具，下面"
 "是其他的一些文档和指导资源："
 
-#: ../../source/getting_started/using_xinference.rst:475
+#: ../../source/getting_started/using_xinference.rst:478
 msgid ""
 ":ref:`How to Use Client APIs for Different Types of Models "
 "<user_guide_client_api>`"
 msgstr ":ref:`如何使用 Python 创建不同类型的模型 <user_guide_client_api>`"
 
-#: ../../source/getting_started/using_xinference.rst:477
+#: ../../source/getting_started/using_xinference.rst:480
 msgid ":ref:`Choosing the Right Backends for Your Needs <user_guide_backends>`"
 msgstr ":ref:`选择正确的推理引擎 <user_guide_backends>` "

doc/source/user_guide/client_api.rst

@@ -137,6 +137,7 @@ Output:
 
     ChatCompletion(id='chatcmpl-ad2f383f-31c7-47d9-87b7-3abe928e629c', choices=[Choice(finish_reason='tool_calls', index=0, message=ChatCompletionMessage(content="```python\ntool_call(loc=94704, type='plus', time=10)\n```", role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_ad2f383f-31c7-47d9-87b7-3abe928e629c', function=Function(arguments='{"loc": 94704, "type": "plus", "time": 10}', name='uber_ride'), type='function')]))], created=1704687803, model='chatglm3', object='chat.completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=-1, prompt_tokens=-1, total_tokens=-1))
 
+.. _anthropic_client:
 
 Anthropic Client
 ========================