feat(ascend): update Docker images and documentation

Author: UsernameFull

docker/Dockerfile.A2

@@ -1,4 +1,4 @@
-FROM quay.io/ascend/cann:9.0.0-910b-ubuntu22.04-py3.11
+FROM quay.io/ascend/cann:9.1.0-910b-ubuntu22.04-py3.12-devel
 
 ARG SOC_VERSION="ascend910b1"
 
@@ -27,29 +27,33 @@ RUN pip config set global.index-url https://mirrors.huaweicloud.com/repository/p
 
 WORKDIR /workspace
 
-RUN git clone --depth 1 -b v0.18.0 https://github.com/vllm-project/vllm.git && \
-    git clone --depth 1 -b v0.18.0 https://github.com/vllm-project/vllm-ascend.git
+RUN git clone --depth 1 -b v0.23.0 https://github.com/vllm-project/vllm.git && \
+    git clone --depth 1 -b v0.23.0rc1 https://github.com/vllm-project/vllm-ascend.git
 
 RUN cd vllm && \
-    pip install -r requirements/build.txt && \
     VLLM_TARGET_DEVICE=empty pip install -v -e . && \
     pip uninstall -y triton && \
     pip cache purge && \
     cd ..
 
-RUN pip install torch==2.9.0+cpu torchvision==0.24.0 torchaudio==2.9.0 \
-    --index-url https://download.pytorch.org/whl/cpu
+RUN pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0
 
 RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
     source /usr/local/Ascend/nnal/atb/set_env.sh && \
     cd vllm-ascend && \
-    pip install -r requirements.txt && \
-    SOC_VERSION=${SOC_VERSION} pip install -v -e . --extra-index-url https://download.pytorch.org/whl/cpu
+    git submodule update --init --recursive && \
+    pip install -r requirements.txt --extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi && \
+    SOC_VERSION=${SOC_VERSION} pip install -v -e . --extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi
+
+RUN python3 -m pip install --index-url https://mirrors.huaweicloud.com/repository/pypi/simple \
+        --no-deps torch-npu==2.10.0.post4
 
 WORKDIR /workspace/ROLL
 COPY . .
 
-RUN pip install -r requirements_common.txt
+RUN grep -v '^gem-llm' requirements_common.txt > requirements_npu.txt && \
+    pip install -r requirements_npu.txt && \
+    rm -f requirements_npu.txt
 
 RUN pip install "transformers==4.57.6" "tensorboard==2.20.0"
 

docker/Dockerfile.A3

@@ -1,4 +1,4 @@
-FROM quay.io/ascend/cann:9.0.0-a3-ubuntu22.04-py3.11
+FROM quay.io/ascend/cann:9.1.0-a3-ubuntu22.04-py3.12-devel
 
 ARG SOC_VERSION="ascend910_9391"
 
@@ -27,29 +27,33 @@ RUN pip config set global.index-url https://mirrors.huaweicloud.com/repository/p
 
 WORKDIR /workspace
 
-RUN git clone --depth 1 -b v0.18.0 https://github.com/vllm-project/vllm.git && \
-    git clone --depth 1 -b v0.18.0 https://github.com/vllm-project/vllm-ascend.git
+RUN git clone --depth 1 -b v0.23.0 https://github.com/vllm-project/vllm.git && \
+    git clone --depth 1 -b v0.23.0rc1 https://github.com/vllm-project/vllm-ascend.git
 
 RUN cd vllm && \
-    pip install -r requirements/build.txt && \
     VLLM_TARGET_DEVICE=empty pip install -v -e . && \
     pip uninstall -y triton && \
     pip cache purge && \
     cd ..
 
-RUN pip install torch==2.9.0+cpu torchvision==0.24.0 torchaudio==2.9.0 \
-    --index-url https://download.pytorch.org/whl/cpu
+RUN pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0
 
 RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
     source /usr/local/Ascend/nnal/atb/set_env.sh && \
     cd vllm-ascend && \
-    pip install -r requirements.txt && \
-    SOC_VERSION=${SOC_VERSION} pip install -v -e . --extra-index-url https://download.pytorch.org/whl/cpu
+    git submodule update --init --recursive && \
+    pip install -r requirements.txt --extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi && \
+    SOC_VERSION=${SOC_VERSION} pip install -v -e . --extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi
+
+RUN python3 -m pip install --index-url https://mirrors.huaweicloud.com/repository/pypi/simple \
+        --no-deps torch-npu==2.10.0.post4
 
 WORKDIR /workspace/ROLL
 COPY . .
 
-RUN pip install -r requirements_common.txt
+RUN grep -v '^gem-llm' requirements_common.txt > requirements_npu.txt && \
+    pip install -r requirements_npu.txt && \
+    rm -f requirements_npu.txt
 
 RUN pip install "transformers==4.57.6" "tensorboard==2.20.0"
 

docs_roll/docs/User Guides/Hardware Support/ascend_docker_usage.md

@@ -1,6 +1,6 @@
 # Running ROLL on Ascend NPU with Docker
 
-Last updated: 06/23/2026.
+Last updated: 08/08/2026.
 
 This guide explains how to get, build, and run ROLL images on **Huawei Ascend NPU**. Prefer the pre-built image when possible; use `Dockerfile.A2` or `Dockerfile.A3` when you need to customize dependencies. Ascend 950 currently follows the manual installation profile in [ROLL x Ascend](ascend_usage.md).
 
@@ -10,8 +10,8 @@ This guide explains how to get, build, and run ROLL images on **Huawei Ascend NP
 | ---- | ------------- | ------------- |
 | Hardware | Atlas 900 A2 PODc (Ascend 910B1) | Atlas 900 A3 PODc (Ascend 910_9391) |
 | Host OS | Ubuntu 22.04 | Ubuntu 22.04 |
-| CANN | 9.0.0 | 9.0.0 |
-| Python | 3.11 | 3.11 |
+| CANN | 9.1.0 | 9.1.0 |
+| Python | 3.12 | 3.12 |
 | Docker | >= 20.10 | >= 20.10 |
 | Ascend NPU Driver | Installed on host | Installed on host |
 
@@ -23,9 +23,10 @@ Both Dockerfiles install the same versions of core dependencies:
 
 | Component | Version |
 | --------- | ------- |
-| PyTorch | 2.9.0+cpu |
-| vLLM | 0.18.0 |
-| vLLM-Ascend | 0.18 |
+| PyTorch | 2.10.0 |
+| torch-npu | 2.10.0.post4 |
+| vLLM | 0.23.0 |
+| vLLM-Ascend | 0.23.0rc1 |
 | Transformers | 4.57.6 |
 | triton-ascend | 3.2.1 |
 
@@ -42,7 +43,7 @@ The primary difference is the base image and SOC version:
 
 | Item | Dockerfile.A2 | Dockerfile.A3 |
 | ---- | ------------- | ------------- |
-| Base Image | `quay.io/ascend/cann:9.0.0-910b-ubuntu22.04-py3.11` | `quay.io/ascend/cann:9.0.0-a3-ubuntu22.04-py3.11` |
+| Base Image | `quay.io/ascend/cann:9.1.0-910b-ubuntu22.04-py3.12-devel` | `quay.io/ascend/cann:9.1.0-a3-ubuntu22.04-py3.12-devel` |
 | SOC_VERSION | `ascend910b1` | `ascend910_9391` |
 
 ## Get the Docker Image

docs_roll/docs/User Guides/Hardware Support/ascend_usage.md

@@ -1,6 +1,6 @@
 # ROLL x Ascend
 
-Last updated: 06/23/2026.
+Last updated: 08/08/2026.
 
 We have added support for Huawei Ascend devices in ROLL.
 
@@ -23,7 +23,7 @@ Supported operating systems:
 | Deployment scenario | Supported OS | Notes |
 | ------------------- | ------------ | ----- |
 | Physical host | Ubuntu 22.04 | Recommended and validated by the current ROLL Ascend guides. |
-| ROLL Ascend container | Ubuntu 22.04 | The A2/A3 Dockerfiles are based on `quay.io/ascend/cann:9.0.0-*-ubuntu22.04-py3.11`. |
+| ROLL Ascend container | Ubuntu 22.04 | The A2/A3 Dockerfiles are based on `quay.io/ascend/cann:9.1.0-*-ubuntu22.04-py3.12-devel`. |
 | Ascend 950 manual installation | Ubuntu 22.04 | Use the Ascend 950-specific torch/vLLM stack below. Keep the driver, firmware, CANN, and `torch_npu` versions aligned with the target Ascend 950 environment. |
 | VM/container deployments on other host OS versions | Follow Ascend/CANN compatibility guidance | Check the Ascend compatibility query assistant and the CANN Software Installation OS compatibility notes for the target hardware. |
 
@@ -33,8 +33,8 @@ Supported operating systems:
 
 | Software | Version |
 | -------- |---------|
-| Python   | 3.11    |
-| CANN     | 9.0.0   |
+| Python   | 3.12    |
+| CANN     | 9.1.0   |
 
 For Ascend 950 , keep Python 3.11 and use the Ascend 950-specific torch/vLLM stack described in [Ascend 950 Installation Profile](#Ascend 950-installation-profile).
 
@@ -43,7 +43,7 @@ For Ascend 950 , keep Python 3.11 and use the Ascend 950-specific torch/vLLM sta
 Use the following commands to create a new conda environment in Miniconda:
 
 ```
-conda create --name roll python=3.11
+conda create --name roll python=3.12
 conda activate roll
 ```
 
@@ -53,10 +53,10 @@ To use torch and torch_npu in ROLL, install them using the commands below:
 
 ```
 # Use CPU-only torch when installing outside the pre-built image
-pip install torch==2.9.0 torchvision==0.24.0 torchaudio==2.9.0 --index-url https://download.pytorch.org/whl/cpu
+pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 --index-url https://download.pytorch.org/whl/cpu
 
 # Install the torch_npu version matching torch/CANN
-pip install torch_npu==2.9.0
+pip install torch_npu==2.10.0.post4
 ```
 
 ### Install vllm & vllm-ascend
@@ -65,28 +65,28 @@ To use vllm in ROLL, compile and install vllm and vllm-ascend as follows:
 
 ```
 # vllm
-git clone -b v0.18.0 --depth 1 https://github.com/vllm-project/vllm.git
+git clone -b v0.23.0 --depth 1 https://github.com/vllm-project/vllm.git
 cd vllm
-pip install -r requirements/build.txt
 
 VLLM_TARGET_DEVICE=empty pip install -v -e .
 cd ..
 
 # vllm-ascend
-git clone -b v0.18.0 --depth 1 https://github.com/vllm-project/vllm-ascend.git
+git clone -b v0.23.0rc1 --depth 1 https://github.com/vllm-project/vllm-ascend.git
 cd vllm-ascend
+git submodule update --init --recursive
 
 pip install -e .
 cd ..
 ```
 
 Or you could install `vllm` and `vllm-ascend` from pre-built wheel:
 ```
-# Install vllm-project/vllm. The newest supported version is v0.18.0.
-pip install vllm==0.18.0
+# Install vllm-project/vllm. The newest supported version is v0.23.0.
+pip install vllm==0.23.0
 
 # Install vllm-project/vllm-ascend from pypi.
-pip install vllm-ascend==0.18
+pip install vllm-ascend==0.23.0rc1
 ```
 
 ### Ascend 950 Installation Profile

docs_roll/i18n/zh-Hans/docusaurus-plugin-content-docs/current/User Guides/Hardware Support/ascend_docker_usage.md

@@ -1,6 +1,6 @@
 # 使用 Docker 在昇腾 NPU 上运行 ROLL
 
-最后更新：2026/06/23。
+最后更新：2026/08/08。
 
 本指南介绍如何在**华为昇腾 NPU** 上获取、构建并运行 ROLL 镜像。推荐优先使用预构建镜像；如需自定义依赖，再使用 `Dockerfile.A2` 或 `Dockerfile.A3` 构建。Atlas 950 当前使用 [ROLL x Ascend](ascend_usage.md) 中的手动安装配置。
 
@@ -10,8 +10,8 @@
 | ---- | ------------- | ------------- |
 | 硬件 | Atlas 900 A2 PODc（Ascend 910B1） | Atlas 900 A3 PODc（Ascend 910_9391） |
 | 宿主机操作系统 | Ubuntu 22.04 | Ubuntu 22.04 |
-| CANN | 9.0.0 | 9.0.0 |
-| Python | 3.11 | 3.11 |
+| CANN | 9.1.0 | 9.1.0 |
+| Python | 3.12 | 3.12 |
 | Docker | >= 20.10 | >= 20.10 |
 | 昇腾 NPU 驱动 | 已安装在宿主机上 | 已安装在宿主机上 |
 
@@ -23,9 +23,10 @@
 
 | 组件 | 版本 |
 | ---- | ---- |
-| PyTorch | 2.9.0+cpu |
-| vLLM | 0.18.0 |
-| vLLM-Ascend | 0.18 |
+| PyTorch | 2.10.0 |
+| torch-npu | 2.10.0.post4 |
+| vLLM | 0.23.0 |
+| vLLM-Ascend | 0.23.0rc1 |
 | Transformers | 4.57.6 |
 | triton-ascend | 3.2.1 |
 
@@ -42,7 +43,7 @@ Ascend 950 使用更新的手动安装版本组合：
 
 | 项目 | Dockerfile.A2 | Dockerfile.A3 |
 | ---- | ------------- | ------------- |
-| 基础镜像 | `quay.io/ascend/cann:9.0.0-910b-ubuntu22.04-py3.11` | `quay.io/ascend/cann:9.0.0-a3-ubuntu22.04-py3.11` |
+| 基础镜像 | `quay.io/ascend/cann:9.1.0-910b-ubuntu22.04-py3.12-devel` | `quay.io/ascend/cann:9.1.0-a3-ubuntu22.04-py3.12-devel` |
 | SOC_VERSION | `ascend910b1` | `ascend910_9391` |
 
 ## 获取 Docker 镜像

docs_roll/i18n/zh-Hans/docusaurus-plugin-content-docs/current/User Guides/Hardware Support/ascend_usage.md

@@ -1,6 +1,6 @@
 # ROLL x Ascend
 
-最后更新：2026/06/23。
+最后更新：2026/08/08。
 
 我们在 ROLL 上增加对华为昇腾设备的支持。
 
@@ -23,7 +23,7 @@ ROLL 昇腾适配当前覆盖以下训练系列硬件：
 | 部署场景 | 支持的操作系统 | 说明 |
 | -------- | -------------- | ---- |
 | 物理机宿主机 | Ubuntu 22.04 | 当前 ROLL 昇腾文档推荐并验证的宿主机操作系统。 |
-| ROLL 昇腾容器 | Ubuntu 22.04 | A2/A3 Dockerfile 基于 `quay.io/ascend/cann:9.0.0-*-ubuntu22.04-py3.11`。 |
+| ROLL 昇腾容器 | Ubuntu 22.04 | A2/A3 Dockerfile 基于 `quay.io/ascend/cann:9.1.0-*-ubuntu22.04-py3.12-devel`。 |
 | Ascend 950  手动安装 | Ubuntu 22.04 | 使用下文 Ascend 950 专用 torch/vLLM 版本组合。驱动、固件、CANN 和 `torch_npu` 版本需要与目标 Ascend 950 环境匹配。 |
 | 其他宿主机 OS 上的虚拟机或容器部署 | 以昇腾/CANN 兼容性说明为准 | 请结合目标硬件查询昇腾兼容性查询助手，以及 CANN 软件安装文档中的操作系统兼容性说明。 |
 
@@ -33,8 +33,8 @@ ROLL 昇腾适配当前覆盖以下训练系列硬件：
 
 | 软件 | 版本 |
 |-----------|-------------|
-| Python    |  3.11       |
-| CANN      |  9.0.0      |
+| Python    |  3.12       |
+| CANN      |  9.1.0      |
 
 Ascend 950 请保持 Python 3.11，并使用下文 [Ascend 950 安装配置](#Ascend 950-安装配置) 中的专用 torch/vLLM 版本组合。
 
@@ -43,7 +43,7 @@ Ascend 950 请保持 Python 3.11，并使用下文 [Ascend 950 安装配置](#As
 使用以下命令在 Miniconda 中创建新的 conda 环境：
 
 ```
-conda create --name roll python=3.11
+conda create --name roll python=3.12
 conda activate roll
 ```
 
@@ -53,10 +53,10 @@ conda activate roll
 
 ```
 # 在预构建镜像外手动安装时，使用 CPU 版 torch
-pip install torch==2.9.0 torchvision==0.24.0 torchaudio==2.9.0 --index-url https://download.pytorch.org/whl/cpu
+pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 --index-url https://download.pytorch.org/whl/cpu
 
 # 安装与 torch/CANN 匹配的 torch_npu
-pip install torch_npu==2.9.0
+pip install torch_npu==2.10.0.post4
 ```
 
 ### 安装 vllm & vllm-ascend
@@ -65,16 +65,16 @@ pip install torch_npu==2.9.0
 
 ```
 # vllm
-git clone -b v0.18.0 --depth 1 https://github.com/vllm-project/vllm.git
+git clone -b v0.23.0 --depth 1 https://github.com/vllm-project/vllm.git
 cd vllm
-pip install -r requirements/build.txt
 
 VLLM_TARGET_DEVICE=empty pip install -v -e .
 cd ..
 
 # vllm-ascend
-git clone -b v0.18.0 --depth 1 https://github.com/vllm-project/vllm-ascend.git
+git clone -b v0.23.0rc1 --depth 1 https://github.com/vllm-project/vllm-ascend.git
 cd vllm-ascend
+git submodule update --init --recursive
 
 pip install -e .
 cd ..
@@ -83,11 +83,11 @@ cd ..
 或者可以从预编译的 wheel 包安装 `vllm` 和 `vllm-ascend`：
 
 ```
-# 安装 vllm-project/vllm，最新支持版本为 v0.18.0
-pip install vllm==0.18.0
+# 安装 vllm-project/vllm，最新支持版本为 v0.23.0
+pip install vllm==0.23.0
 
 # 从 pypi 安装 vllm-project/vllm-ascend
-pip install vllm-ascend==0.18
+pip install vllm-ascend==0.23.0rc1
 ```
 
 ### Ascend 950 安装配置