xLLM-AI · XuZhang99 · Jul 6, 2026 · Jul 6, 2026
diff --git a/README.md b/README.md
@@ -3,7 +3,7 @@
 [English](./README.md) | [简体中文](./README.zh-CN.md)
 
 This repository contains the Astro + Starlight documentation site for
-[xLLM](https://github.com/jd-opensource/xllm), an LLM inference framework for
+[xLLM](https://github.com/xLLM-AI/xllm), an LLM inference framework for
 high-performance serving on domestic AI accelerators.
 
 The site is built with Starlight and `starlight-theme-rapide`. It includes a
@@ -85,4 +85,4 @@ npm run preview
 
 ## Related Repository
 
-- xLLM source code: <https://github.com/jd-opensource/xllm>
+- xLLM source code: <https://github.com/xLLM-AI/xllm>
diff --git a/README.zh-CN.md b/README.zh-CN.md
@@ -2,7 +2,7 @@
 
 [English](./README.md) | [简体中文](./README.zh-CN.md)
 
-本仓库是 [xLLM](https://github.com/jd-opensource/xllm) 的 Astro + Starlight
+本仓库是 [xLLM](https://github.com/xLLM-AI/xllm) 的 Astro + Starlight
 文档站。xLLM 是面向国产 AI 加速器的高性能大语言模型推理框架。
 
 站点基于 Starlight 和 `starlight-theme-rapide` 构建，包含自定义顶部导航、
@@ -81,4 +81,4 @@ npm run preview
 
 ## 相关仓库
 
-- xLLM 源码：<https://github.com/jd-opensource/xllm>
+- xLLM 源码：<https://github.com/xLLM-AI/xllm>
diff --git a/src/content/docs/en/cookbook/autoregressive_models/glm/glm_5.md b/src/content/docs/en/cookbook/autoregressive_models/glm/glm_5.md
@@ -3,7 +3,7 @@ title: "GLM-5 / GLM-5.1 / GLM-5.2"
 sidebar:
   order: 2
 ---
-+ Source code: https://github.com/jd-opensource/xllm
++ Source code: https://github.com/xLLM-AI/xllm
 
 + Available in China: https://gitcode.com/xLLM-AI/xllm
 
@@ -57,7 +57,7 @@ sudo docker run -it --ipc=host -u 0 --privileged --name mydocker --network=host
 Download the official repository and module dependencies:
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm 
 git checkout release/v0.10.0
 git submodule update --init --recursive
@@ -339,15 +339,15 @@ msmodelslim quant \
 
 #### PD Disaggregated Deployment
 
-`xllm` supports PD disaggregated deployment. This must be used together with another open-source library, [xllm service](https://github.com/jd-opensource/xllm-service).
+`xllm` supports PD disaggregated deployment. This must be used together with another open-source library, [xllm service](https://github.com/xLLM-AI/xllm-service).
 
 ##### xLLM Service Dependencies
 
 First, download and install `xllm service`, similar to installing and building `xllm`:
 
 ```bash
-git clone https://github.com/jd-opensource/xllm-service
-cd xllm_service
+git clone https://github.com/xLLM-AI/xllm-service.git
+cd xllm-service
 git submodule init
 git submodule update
 ```

diff --git a/src/content/docs/en/cookbook/autoregressive_models/kimi/kimi2_5.md b/src/content/docs/en/cookbook/autoregressive_models/kimi/kimi2_5.md
@@ -4,7 +4,7 @@ sidebar:
   order: 2
 ---
 
-- Source code: [https://github.com/jd-opensource/xllm](https://github.com/jd-opensource/xllm)
+- Source code: [https://github.com/xLLM-AI/xllm](https://github.com/xLLM-AI/xllm)
 - Available in China: [https://gitcode.com/xLLM-AI/xllm](https://gitcode.com/xLLM-AI/xllm)
 - Kimi-K2.5 W8A8 weight download: [modelscope-Kimi-K2.5-W8A8-xLLM](https://www.modelscope.cn/models/Eco-Tech/Kimi-K2.5-W8A8-xLLM)
 - Kimi-K2.6 W8A8 weight download: [modelscope-Kimi-K2.6-w8a8-xllm](https://www.modelscope.cn/models/Eco-Tech/Kimi-K2.6-w8a8-xllm)
@@ -55,7 +55,7 @@ sudo docker run -it --ipc=host -u 0 --privileged --name xllm_kimi_k25 --network=
 Download the official repository and module dependencies:
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 git checkout main
 git submodule init

diff --git a/src/content/docs/en/cookbook/autoregressive_models/minmax/minmax_m2_7.md b/src/content/docs/en/cookbook/autoregressive_models/minmax/minmax_m2_7.md
@@ -4,7 +4,7 @@ sidebar:
   order: 3
 ---
 
-+ Source code: https://github.com/jd-opensource/xllm
++ Source code: https://github.com/xLLM-AI/xllm
 
 + Available in China: https://gitcode.com/xLLM-AI/xllm
 
@@ -73,7 +73,7 @@ sudo docker run -it --ipc=host -u 0 --privileged --name xllm_minimax --network=h
 Download the official repository and module dependencies:
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 git checkout preview/minimax-minimal
 git submodule init

diff --git a/src/content/docs/en/cookbook/autoregressive_models/qwen/qwen3_5.md b/src/content/docs/en/cookbook/autoregressive_models/qwen/qwen3_5.md
@@ -4,7 +4,7 @@ sidebar:
   order: 1
 ---
 
-+ Source code: https://github.com/jd-opensource/xllm
++ Source code: https://github.com/xLLM-AI/xllm
 
 + Available in China: https://gitcode.com/xLLM-AI/xllm
 
@@ -57,7 +57,7 @@ docker run -it -d \
 Download the official repository and module dependencies:
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 pip install pre-commit
 pre-commit install

diff --git a/src/content/docs/en/cookbook/diffusion_models/flux/flux2.md b/src/content/docs/en/cookbook/diffusion_models/flux/flux2.md
@@ -7,7 +7,7 @@ sidebar:
 
 This section will collect Flux2 diffusion model inference recipes for xLLM.
 
-+ Source code: https://github.com/jd-opensource/xllm
++ Source code: https://github.com/xLLM-AI/xllm
 
 + Available in China: https://gitcode.com/xLLM-AI/xllm
 
@@ -57,7 +57,7 @@ docker exec -it $CONTAINER bash
 Download the official repository and module dependencies:
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 
 ```

diff --git a/src/content/docs/en/features/disagg_pd.md b/src/content/docs/en/features/disagg_pd.md
@@ -20,7 +20,7 @@ The overall architecture is shown below:
 ### Preparation
 #### Install Dependencies
 - **xLLM**: Refer to [Installation && Compilation](/en/getting_started/quick_start/)
-- **xLLM Service**: Refer to [xLLM Service](https://github.com/jd-opensource/xllm-service)
+- **xLLM Service**: Refer to [xLLM Service](https://github.com/xLLM-AI/xllm-service)
 
 #### Obtain Environment Information  
 Deploying Disaggregated PD Service requires obtaining the Device IP of the machine to create communication resources. Execute the command `cat /etc/hccn.conf | grep address` on the current AI Server to get the Device IP, for example:

diff --git a/src/content/docs/en/features/global_kvcache.md b/src/content/docs/en/features/global_kvcache.md
@@ -21,7 +21,7 @@ The overall architecture is shown in the diagram below:
 
 #### Install Dependencies
 - **xLLM**: Refer to [Quick Start](/en/getting_started/quick_start/)
-- **xLLM Service**: Refer to [xLLM Service](https://github.com/jd-opensource/xllm-service)
+- **xLLM Service**: Refer to [xLLM Service](https://github.com/xLLM-AI/xllm-service)
 
 ### Usage Instructions
 

diff --git a/src/content/docs/en/features/xllm_service_overview.md b/src/content/docs/en/features/xllm_service_overview.md
@@ -3,7 +3,7 @@ title: "xLLM Service"
 sidebar:
   order: 90
 ---
-[:simple-github: xLLM Service](https://github.com/jd-opensource/xllm-service)
+[:simple-github: xLLM Service](https://github.com/xLLM-AI/xllm-service)
 
 ## Project Overview
 

diff --git a/src/content/docs/en/getting_started/offline_service.md b/src/content/docs/en/getting_started/offline_service.md
@@ -7,9 +7,9 @@ To facilitate users in quickly using xLLM for offline inference, we provide Pyth
 
 ## LLM
 
-LLM inference example: [:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate.py)
+LLM inference example: [:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate.py)
 
-LLM Beam Search example: [:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate_beam_search.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate_beam_search.py)
+LLM Beam Search example: [:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate_beam_search.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate_beam_search.py)
 
 Use `BeamSearchParams` with `beam_width` greater than `1`, then call `llm.beam_search(...)`:
 
@@ -36,8 +36,8 @@ For LLM Beam Search, use `beam_width` as the switch. `top_logprobs` controls the
 
 ## Embedding
 
-Generate embedding example: [:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate_embedding.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate_embedding.py)
+Generate embedding example: [:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate_embedding.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate_embedding.py)
 
 ## VLM
 
-VLM inference example: [:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate_vlm.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate_vlm.py)
+VLM inference example: [:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate_vlm.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate_vlm.py)
diff --git a/src/content/docs/en/getting_started/quick_start.md b/src/content/docs/en/getting_started/quick_start.md
@@ -47,7 +47,7 @@ docker run -it \
 
 ### NVIDIA GPU
 
-We provide a [Dockerfile](https://github.com/jd-opensource/xllm/blob/main/docker/Dockerfile.cuda) for NVIDIA GPU usage, which can be used to build custom image. Of course, you can also use dev image we built based on the default Dockerfile:
+We provide a [Dockerfile](https://github.com/xLLM-AI/xllm/blob/main/docker/Dockerfile.cuda) for NVIDIA GPU usage, which can be used to build custom image. Of course, you can also use dev image we built based on the default Dockerfile:
 ```bash
 docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-cuda-x86
 ```
@@ -148,7 +148,7 @@ If you download a release image, i.e., an image with a version number in the tag
 
 Download xllm and dependencies:
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 
 # Install pre-commit for the first time

diff --git a/src/content/docs/zh/cookbook/autoregressive_models/glm/glm_5.md b/src/content/docs/zh/cookbook/autoregressive_models/glm/glm_5.md
@@ -4,7 +4,7 @@ sidebar:
   order: 2
 ---
 
-+ 源码地址：https://github.com/jd-opensource/xllm
++ 源码地址：https://github.com/xLLM-AI/xllm
 
 + 国内可用: https://gitcode.com/xLLM-AI/xllm
 
@@ -58,7 +58,7 @@ sudo docker run -it --ipc=host -u 0 --privileged --name mydocker --network=host
 下载官方仓库与模块依赖：
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 git checkout release/v0.10.0
 git submodule update --init --recursive
@@ -330,15 +330,15 @@ msmodelslim quant \
 
 #### PD分离部署
 
-`xllm`支持PD分离部署，这需要与另一个开源库[xllm service](https://github.com/jd-opensource/xllm-service)配套使用。
+`xllm`支持PD分离部署，这需要与另一个开源库[xllm service](https://github.com/xLLM-AI/xllm-service)配套使用。
 
 ##### xLLM Service依赖
 
 首先，我们下载安装`xllm service`，与安装编译`xllm`类似：
 
 ```bash
-git clone https://github.com/jd-opensource/xllm-service
-cd xllm_service
+git clone https://github.com/xLLM-AI/xllm-service.git
+cd xllm-service
 git submodule init
 git submodule update
 ```

diff --git a/src/content/docs/zh/cookbook/autoregressive_models/kimi/kimi2_5.md b/src/content/docs/zh/cookbook/autoregressive_models/kimi/kimi2_5.md
@@ -4,7 +4,7 @@ sidebar:
   order: 2
 ---
 
-- 源码地址：[https://github.com/jd-opensource/xllm](https://github.com/jd-opensource/xllm)
+- 源码地址：[https://github.com/xLLM-AI/xllm](https://github.com/xLLM-AI/xllm)
 - 国内可用: [https://gitcode.com/xLLM-AI/xllm](https://gitcode.com/xLLM-AI/xllm)
 - Kimi-K2.5 W8A8权重下载: [modelscope-Kimi-K2.5-W8A8-xLLM](https://www.modelscope.cn/models/Eco-Tech/Kimi-K2.5-W8A8-xLLM)
 - Kimi-K2.6 W8A8权重下载: [modelscope-Kimi-K2.6-w8a8-xllm](https://www.modelscope.cn/models/Eco-Tech/Kimi-K2.6-w8a8-xllm)
@@ -55,7 +55,7 @@ sudo docker run -it --ipc=host -u 0 --privileged --name xllm_kimi_k25 --network=
 下载官方仓库与模块依赖：
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 git checkout main
 git submodule init

diff --git a/src/content/docs/zh/cookbook/autoregressive_models/minmax/minmax_m2_7.md b/src/content/docs/zh/cookbook/autoregressive_models/minmax/minmax_m2_7.md
@@ -4,7 +4,7 @@ sidebar:
   order: 3
 ---
 
-+ 源码地址：https://github.com/jd-opensource/xllm
++ 源码地址：https://github.com/xLLM-AI/xllm
 
 + 国内可用: https://gitcode.com/xLLM-AI/xllm
 
@@ -73,7 +73,7 @@ sudo docker run -it --ipc=host -u 0 --privileged --name xllm_minimax --network=h
 下载官方仓库与模块依赖：
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 git checkout preview/minimax-minimal
 git submodule init

diff --git a/src/content/docs/zh/cookbook/autoregressive_models/qwen/qwen3_5.md b/src/content/docs/zh/cookbook/autoregressive_models/qwen/qwen3_5.md
@@ -4,7 +4,7 @@ sidebar:
   order: 1
 ---
 
-+ 源码地址：https://github.com/jd-opensource/xllm
++ 源码地址：https://github.com/xLLM-AI/xllm
 
 + 国内可用: https://gitcode.com/xLLM-AI/xllm
 
@@ -57,7 +57,7 @@ docker run -it -d \
 下载官方仓库与模块依赖：
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 pip install pre-commit
 pre-commit install

diff --git a/src/content/docs/zh/cookbook/diffusion_models/flux/flux2.md b/src/content/docs/zh/cookbook/diffusion_models/flux/flux2.md
@@ -7,7 +7,7 @@ sidebar:
 
 本章节用于汇总 Flux2 扩散模型在 xLLM 中的推理实践。
 
-+ 源码地址：https://github.com/jd-opensource/xllm
++ 源码地址：https://github.com/xLLM-AI/xllm
 
 + 国内可用: https://gitcode.com/xLLM-AI/xllm
 
@@ -58,7 +58,7 @@ docker exec -it $CONTAINER bash
 下载官方仓库与模块依赖：
 
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm 
 
 ```

diff --git a/src/content/docs/zh/features/disagg_pd.md b/src/content/docs/zh/features/disagg_pd.md
@@ -18,7 +18,7 @@ xLLM PD分离功能主要通过以下三个模块实现：
 ### 使用准备
 #### 安装相关依赖
 - **xLLM**: 参见[安装编译](/zh/getting_started/quick_start/)
-- **xLLM Service**: 参见[xLLM Service](https://github.com/jd-opensource/xllm-service)
+- **xLLM Service**: 参见[xLLM Service](https://github.com/xLLM-AI/xllm-service)
 
 ### 启动PD分离服务
 1. 启动etcd

diff --git a/src/content/docs/zh/features/global_kvcache.md b/src/content/docs/zh/features/global_kvcache.md
@@ -18,7 +18,7 @@ xLLM 全局KV Cache功能主要通过以下三个模块实现：
 ### 使用准备
 #### 安装相关依赖
 - **xLLM**: 参见[快速开始](/zh/getting_started/quick_start/)
-- **xLLM Service**: 参见[xLLM Service](https://github.com/jd-opensource/xllm-service)
+- **xLLM Service**: 参见[xLLM Service](https://github.com/xLLM-AI/xllm-service)
 
 ### 使用方式
 1. etcd启动配置：

diff --git a/src/content/docs/zh/features/xllm_service_overview.md b/src/content/docs/zh/features/xllm_service_overview.md
@@ -3,7 +3,7 @@ title: "xLLM Service"
 sidebar:
   order: 90
 ---
-[:simple-github: xLLM Service](https://github.com/jd-opensource/xllm-service)
+[:simple-github: xLLM Service](https://github.com/xLLM-AI/xllm-service)
 
 ## 简介
 

diff --git a/src/content/docs/zh/getting_started/offline_service.md b/src/content/docs/zh/getting_started/offline_service.md
@@ -7,9 +7,9 @@ sidebar:
 
 ## LLM
 
-LLM推理示例：[:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate.py)
+LLM推理示例：[:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate.py)
 
-LLM Beam Search 示例：[:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate_beam_search.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate_beam_search.py)
+LLM Beam Search 示例：[:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate_beam_search.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate_beam_search.py)
 
 使用 `BeamSearchParams` 设置大于 `1` 的 `beam_width`，然后调用 `llm.beam_search(...)`：
 
@@ -36,9 +36,9 @@ LLM Beam Search 使用 `beam_width` 作为开启参数。`top_logprobs` 控制
 
 ## Embedding
 
-生成Embedding示例：[:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate_embedding.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate_embedding.py)
+生成Embedding示例：[:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate_embedding.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate_embedding.py)
 
 ## VLM
 
-VLM推理示例：[:simple-github: https://github.com/jd-opensource/xllm/blob/main/examples/generate_vlm.py](https://github.com/jd-opensource/xllm/blob/main/examples/generate_vlm.py)
+VLM推理示例：[:simple-github: https://github.com/xLLM-AI/xllm/blob/main/examples/generate_vlm.py](https://github.com/xLLM-AI/xllm/blob/main/examples/generate_vlm.py)
 
diff --git a/src/content/docs/zh/getting_started/quick_start.md b/src/content/docs/zh/getting_started/quick_start.md
@@ -47,7 +47,7 @@ docker run -it \
 
 ### NVIDIA GPU
 
-我们提供了NVIDIA GPU使用的[Dockerfile](https://github.com/jd-opensource/xllm/blob/main/docker/Dockerfile.cuda)，可以构建自定义镜像，当然也可以使用我们根据默认Dockerfile构建的开发镜像：
+我们提供了NVIDIA GPU使用的[Dockerfile](https://github.com/xLLM-AI/xllm/blob/main/docker/Dockerfile.cuda)，可以构建自定义镜像，当然也可以使用我们根据默认Dockerfile构建的开发镜像：
 ```bash
 docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-cuda-x86
 ```
@@ -148,7 +148,7 @@ docker run -it \
 
 下载xllm及依赖
 ```bash
-git clone https://github.com/jd-opensource/xllm
+git clone https://github.com/xLLM-AI/xllm.git
 cd xllm
 
 # 第一次需要进行pre-commit安装