pytorch主干nightly集成验证

.ci/docker/README.md

@@ -0,0 +1,49 @@
+# torch-npu CI Docker Images
+
+本目录管理 torch-npu 项目的测试镜像 (test)，当前仅支持 aarch64 架构。
+
+## 镜像类型
+
+| 类型 | 基座 | 用途 |
+|------|------|------|
+| **test** | ubuntu:22.04 | CI 单元测试运行环境，包含 PyTorch nightly、CANN runtime、triton-ascend 和测试框架 |
+
+## 目录结构
+
+```
+.ci/docker/
+├── README.md
+├── requirements-test.txt         # Test 镜像 pip 依赖
+├── docker_build.sh               # 构建入口脚本
+├── common/                       # 共享安装脚本
+│   ├── install_cann.sh           # 安装 CANN toolkit (支持 A2/A3)
+│   ├── install_triton.sh         # 安装 triton-ascend
+│   └── install_obs.sh            # 安装华为 OBS util
+└── test/
+    └── Dockerfile.aarch64
+```
+
+## 快速构建
+
+```bash
+./docker_build.sh torch-npu-test-aarch64-cann-a2-py3.10-torch-nightly
+./docker_build.sh torch-npu-test-aarch64-cann-a3-py3.10-torch-nightly
+```
+
+## Tag 命名规范
+
+```
+torch-npu-test-aarch64-cann<CHIP>-py<PYTHON_VERSION>-torch-nightly
+```
+
+| 字段 | 可选值 |
+|------|--------|
+| CHIP | A2 (Ascend 910b), A3 |
+| PYTHON_VERSION | 3.10 |
+
+## CANN 芯片映射
+
+| CANN_CHIP | 芯片 | CANN 版本 |
+|-----------|------|----------|
+| A2 | Ascend 910b | 9.1.0-beta.1 |
+| A3 | Ascend A3 | 9.0.0-beta.2 |

.ci/docker/common/install_cann.sh

@@ -0,0 +1,109 @@
+#!/usr/bin/bash
+# Install CANN toolkit for Ascend NPU.
+# Usage: CANN_CHIP=A1 ./install_cann.sh
+#   CANN_CHIP: A1 (Ascend 910), A2 (Ascend 910b), A3 (Ascend A3)
+# Automatically detects architecture (x86_64 / aarch64).
+
+set -e
+
+CANN_CHIP="${CANN_CHIP:-A1}"
+ARCH=$(uname -m)
+
+BASE_URL="https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/cann-package"
+CANN_BASE_URL="https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%209.1.T1"
+
+case "${ARCH}_${CANN_CHIP}" in
+  # x86_64
+  x86_64_A1)
+    TOOLKIT_URL="${BASE_URL}/20260513/Ascend-cann-toolkit_9.1.0_linux-x86_64.run"
+    OPS_URL="${BASE_URL}/20260513/Ascend-cann-910-ops_9.1.0_linux-x86_64.run"
+    NNAL_URL="${BASE_URL}/20260513/Ascend-cann-nnal_9.1.0_linux-x86_64.run"
+    OPS_GLOB="Ascend-cann-910*"
+    SET_ENV_PATH="/usr/local/Ascend/cann/set_env.sh"
+    ;;
+  x86_64_A2)
+    TOOLKIT_URL="${CANN_BASE_URL}/Ascend-cann-toolkit_9.1.0-beta.1_linux-x86_64.run"
+    OPS_URL="${CANN_BASE_URL}/Ascend-cann-910b-ops_9.1.0-beta.1_linux-x86_64.run"
+    NNAL_URL="${CANN_BASE_URL}/Ascend-cann-nnal_9.1.0-beta.1_linux-x86_64.run"
+    OPS_GLOB="Ascend-cann-910b-ops*"
+    SET_ENV_PATH="/usr/local/Ascend/cann/set_env.sh"
+    ;;
+  x86_64_A3)
+    TOOLKIT_URL="${CANN_BASE_URL}/Ascend-cann-toolkit_9.1.0-beta.1_linux-x86_64.run"
+    OPS_URL="${CANN_BASE_URL}/Ascend-cann-A3-ops_9.1.0-beta.1_linux-x86_64.run"
+    NNAL_URL="${CANN_BASE_URL}/Ascend-cann-nnal_9.1.0-beta.1_linux-x86_64.run"
+    OPS_GLOB="Ascend-cann-A3-ops*"
+    SET_ENV_PATH="/usr/local/Ascend/cann/set_env.sh"
+    ;;
+  # aarch64
+  aarch64_A1)
+    TOOLKIT_URL="${BASE_URL}/20260302/Ascend-cann-toolkit_9.0.0-beta.1_linux-aarch64.run"
+    OPS_URL="${BASE_URL}/20260302/Ascend-cann-910b-ops_9.0.0-beta.1_linux-aarch64.run"
+    NNAL_URL="${BASE_URL}/20260302/Ascend-cann-nnal_9.0.0-beta.1_linux-aarch64.run"
+    OPS_GLOB="Ascend-cann-910b*"
+    SET_ENV_PATH="/usr/local/Ascend/cann/set_env.sh"
+    ;;
+  aarch64_A2)
+    TOOLKIT_URL="${CANN_BASE_URL}/Ascend-cann-toolkit_9.1.0-beta.1_linux-aarch64.run"
+    OPS_URL="${CANN_BASE_URL}/Ascend-cann-910b-ops_9.1.0-beta.1_linux-aarch64.run"
+    NNAL_URL="${CANN_BASE_URL}/Ascend-cann-nnal_9.1.0-beta.1_linux-aarch64.run"
+    OPS_GLOB="Ascend-cann-910b-ops*"
+    SET_ENV_PATH="/usr/local/Ascend/cann/set_env.sh"
+    ;;
+  aarch64_A3)
+    TOOLKIT_URL="${CANN_BASE_URL}/Ascend-cann-toolkit_9.1.0-beta.1_linux-aarch64.run"
+    OPS_URL="${CANN_BASE_URL}/Ascend-cann-A3-ops_9.1.0-beta.1_linux-aarch64.run"
+    NNAL_URL="${CANN_BASE_URL}/Ascend-cann-nnal_9.1.0-beta.1_linux-aarch64.run"
+    OPS_GLOB="Ascend-cann-A3-ops*"
+    SET_ENV_PATH="/usr/local/Ascend/cann/set_env.sh"
+    ;;
+  *)
+    echo "Unsupported combination: ${ARCH} + ${CANN_CHIP}"
+    exit 1
+    ;;
+esac
+
+echo "Installing CANN ${CANN_CHIP} for ${ARCH}..."
+
+echo "=== Creating HwHiAiUser user and group ==="
+groupadd -f HwHiAiUser
+id -u HwHiAiUser >/dev/null 2>&1 || useradd -g HwHiAiUser -d /home/HwHiAiUser -m HwHiAiUser -s /bin/bash
+
+rm -rf cann
+mkdir -p cann && cd cann
+
+echo "=== Downloading CANN packages ==="
+curl -O "${TOOLKIT_URL}"
+curl -O "${OPS_URL}"
+curl -O "${NNAL_URL}"
+echo "Download complete."
+
+chmod +x Ascend-cann*.run
+
+echo "=== Installing CANN toolkit ==="
+./Ascend-cann-toolkit*.run --full --quiet --install-path=/usr/local/Ascend
+source "${SET_ENV_PATH}"
+echo "toolkit install success"
+
+echo "=== Installing CANN ops ==="
+./${OPS_GLOB}.run --install --quiet --install-path=/usr/local/Ascend
+echo "ops install success"
+
+echo "=== Installing CANN nnal ==="
+./Ascend-cann-nnal*.run --install --quiet --install-path=/usr/local/Ascend
+source /usr/local/Ascend/nnal/atb/set_env.sh
+echo "nnal install success"
+
+# Some CANN versions install to versioned paths (e.g. cann-9.0.0-beta.2)
+# instead of /usr/local/Ascend/cann/. Fix broken symlinks so runtime
+# sourcing of set_env.sh works.
+if [ ! -f /usr/local/Ascend/cann/set_env.sh ]; then
+  CANN_REAL_DIR=$(ls -d /usr/local/Ascend/cann-* 2>/dev/null | head -1)
+  if [ -n "${CANN_REAL_DIR}" ]; then
+    ln -sf "${CANN_REAL_DIR}" /usr/local/Ascend/cann
+    echo "Fixed: linked ${CANN_REAL_DIR} -> /usr/local/Ascend/cann"
+  fi
+fi
+
+rm -rf *
+echo "CANN ${CANN_CHIP} installation complete."

.ci/docker/common/install_obs.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/bash
+# Install Huawei OBS util for object storage access.
+
+set -e
+
+ARCH=$(uname -m)
+case "${ARCH}" in
+  x86_64)  OBS_ARCH="amd64" ;;
+  aarch64) OBS_ARCH="arm64" ;;
+  *)       echo "Unsupported architecture: ${ARCH}"; exit 1 ;;
+esac
+
+OBS_URL="https://obs-community.obs.cn-north-1.myhuaweicloud.com/obsutil/current/obsutil_linux_${OBS_ARCH}.tar.gz"
+
+wget -q "${OBS_URL}"
+mkdir -p /usr/local/obsutil
+tar -zxf "obsutil_linux_${OBS_ARCH}.tar.gz" -C /usr/local/obsutil/
+rm -f "obsutil_linux_${OBS_ARCH}.tar.gz"
+ln -sf /usr/local/obsutil/obsutil_linux_${OBS_ARCH}_*/obsutil /usr/local/bin/obsutil
+
+echo "OBS util installed."

.ci/docker/common/install_triton.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/bash
+# Install triton-ascend for NPU.
+# Usage: ./install_triton.sh <PYTHON_VERSION>
+#   PYTHON_VERSION: e.g. 3.10, 3.11, 3.12, 3.13
+
+set -e
+
+TRITON_VERSION="${TRITON_VERSION:-3.2.1}"
+PYTHON_VERSION="${1:?Usage: $0 <PYTHON_VERSION> (e.g. 3.10)}"
+
+ARCH=$(uname -m)
+PY_SHORT=$(echo "${PYTHON_VERSION}" | tr -d '.')
+
+TRITON_WHL="triton_ascend-${TRITON_VERSION}-cp${PY_SHORT}-cp${PY_SHORT}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl"
+TRITON_URL="https://gitcode.com/Ascend/triton-ascend/releases/download/v${TRITON_VERSION}/${TRITON_WHL}"
+
+echo "Installing triton-ascend ${TRITON_VERSION} for Python ${PYTHON_VERSION} (${ARCH})..."
+pip3 install --no-cache-dir "${TRITON_URL}"
+echo "triton-ascend installed."

.ci/docker/docker_build.sh

@@ -0,0 +1,56 @@
+#!/usr/bin/bash
+# Docker image build script for torch-npu CI test images (aarch64 only).
+#
+# Usage:
+#   ./docker_build.sh <IMAGE_TAG>
+#
+# Examples:
+#   ./docker_build.sh torch-npu-test-aarch64-cann-a2-py3.10-torch-nightly
+#   ./docker_build.sh torch-npu-test-aarch64-cann-a3-py3.10-torch-nightly
+
+set -euo pipefail
+
+BASE_TAG="${1:?Usage: $0 <IMAGE_TAG>}"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+BUILD_CONTEXT="${SCRIPT_DIR}"
+
+case "$BASE_TAG" in
+  torch-npu-test-aarch64-cann-a2-py3.10-torch-nightly)
+    CANN_CHIP=A2
+    PYTHON_VERSION=3.10
+    ;;
+  torch-npu-test-aarch64-cann-a3-py3.10-torch-nightly)
+    CANN_CHIP=A3
+    PYTHON_VERSION=3.10
+    ;;
+  *)
+    echo "ERROR: Unknown image tag: $BASE_TAG"
+    echo ""
+    echo "Supported tags:"
+    echo "  torch-npu-test-aarch64-cann-a2-py3.10-torch-nightly"
+    echo "  torch-npu-test-aarch64-cann-a3-py3.10-torch-nightly"
+    exit 1
+    ;;
+esac
+
+TIMESTAMP="$(date +%Y%m%d%H%M)"
+TAG="${BASE_TAG}-${TIMESTAMP}"
+
+DOCKERFILE="${SCRIPT_DIR}/test/Dockerfile.aarch64"
+
+echo "=== Image Configuration ==="
+echo "  Architecture:   aarch64"
+echo "  CANN Chip:      ${CANN_CHIP}"
+echo "  Python:         ${PYTHON_VERSION}"
+echo "  PyTorch:        nightly"
+echo "  Full Tag:       ${TAG}"
+
+echo "=== Building test image: ${TAG} ==="
+docker build \
+  --build-arg CANN_CHIP="${CANN_CHIP}" \
+  --build-arg PYTHON_VERSION="${PYTHON_VERSION}" \
+  --tag "${TAG}" \
+  --file "${DOCKERFILE}" \
+  "${BUILD_CONTEXT}"
+
+echo "=== Image built successfully: ${TAG} ==="

.ci/docker/requirements-post.txt

@@ -0,0 +1,11 @@
+# Python dependencies that require PyTorch to be pre-installed.
+# Install AFTER PyTorch is built, before running tests.
+# Uses PyTorch nightly index to resolve torch-dependent packages.
+
+--index-url https://download.pytorch.org/whl/nightly/cpu
+--extra-index-url https://pypi.org/simple
+-f https://data.pyg.org/whl/torch-2.13.0+cpu.html
+
+torchvision
+torch_geometric==2.5.3
+torch-scatter==2.1.2