[Refactore] [CI] Remove redundant CI test runs step 2 (#17584)

2026-01-24 23:39:48 -08:00
parent 9bd92ba0f6
commit d1042e0d62
36 changed files with 199 additions and 196 deletions
@@ -0,0 +1,66 @@
+#!/bin/bash
+set -euo pipefail
+
+PIP_INSTALL="python3 -m pip install --no-cache-dir"
+DEVICE_TYPE=$1
+
+
+# Install the required dependencies in CI.
+apt update -y && apt install -y \
+    build-essential \
+    cmake \
+    wget \
+    curl \
+    net-tools \
+    zlib1g-dev \
+    lld \
+    clang \
+    locales \
+    ccache \
+    ca-certificates
+update-ca-certificates
+${PIP_INSTALL} --upgrade pip
+# Pin wheel to 0.45.1, REF: https://github.com/pypa/wheel/issues/662
+${PIP_INSTALL} wheel==0.45.1 pybind11
+
+
+### Install MemFabric
+${PIP_INSTALL} memfabric-hybrid==1.0.0
+
+
+### Install PyTorch and PTA
+PYTORCH_VERSION="2.8.0"
+TORCHVISION_VERSION="0.23.0"
+${PIP_INSTALL} torch==${PYTORCH_VERSION} torchvision==${TORCHVISION_VERSION} --index-url https://download.pytorch.org/whl/cpu
+
+PTA_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/torch_npu/torch_npu-2.8.0.post2.dev20251113-cp311-cp311-manylinux_2_28_aarch64.whl"
+${PIP_INSTALL} ${PTA_URL}
+
+
+### Install Triton-Ascend
+TRITON_ASCEND_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/triton_ascend/triton_ascend-3.2.0.dev2025112116-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
+${PIP_INSTALL} ${TRITON_ASCEND_URL}
+
+
+### Install BiSheng
+BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251121.run"
+BISHENG_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/triton_ascend/${BISHENG_NAME}"
+wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
+
+
+### Install sgl-kernel-npu
+SGL_KERNEL_NPU_TAG="2025.12.31"
+git clone --depth 1 https://github.com/sgl-project/sgl-kernel-npu.git --branch ${SGL_KERNEL_NPU_TAG}
+(cd sgl-kernel-npu && bash ./build.sh && ${PIP_INSTALL} output/deep_ep*.whl output/sgl_kernel_npu*.whl && cd "$(python3 -m pip show deep-ep | grep -E '^Location:' | awk '{print $2}')" && ln -s deep_ep/deep_ep_cpp*.so)
+
+
+### Install CustomOps (TODO: to be removed once merged into sgl-kernel-npu)
+wget https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run
+chmod a+x ./CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run
+./CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run --quiet --install-path=/usr/local/Ascend/ascend-toolkit/latest/opp
+wget https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/custom_ops-1.0.$DEVICE_TYPE-cp311-cp311-linux_aarch64.whl
+pip install ./custom_ops-1.0.$DEVICE_TYPE-cp311-cp311-linux_aarch64.whl
+
+### Install SGLang
+rm -rf python/pyproject.toml && mv python/pyproject_other.toml python/pyproject.toml
+${PIP_INSTALL} -v -e "python[dev_npu]"
@@ -0,0 +1,26 @@
+#!/bin/bash
+set -euo pipefail
+
+# Print log information(sglang version, commit sha, sgl-kernel-npu version, sgl-kernel-npu commit sha, npu-smi info and pip list.
+npu-smi info
+pip list
+get_version() {
+    [ -f "$1" ] && python3 -c 'import re, sys; print(sys.argv[2] + " version: v" + re.search(r"__version__\s*=\s*[\"'"'"'](.*?)[\"'"'"']", open(sys.argv[1]).read()).group(1))' "$1" "$2" 2>/dev/null || echo "$2 version: unknown"
+}
+get_version "./python/sglang/version.py" "sglang"
+get_version "./sgl-kernel/python/sgl_kernel/version.py" "sgl_kernel"
+SGLANG_URL="https://github.com/sgl-project/sglang.git"
+SGL_KERNEL_URL="https://github.com/sgl-project/sgl-kernel-npu.git"
+SGLANG_BRANCH="main"
+SGL_KERNEL_BRANCH="main"
+get_sha() {
+    local name="$1"
+    local url="$2"
+    local branch="$3"
+    local sha
+    sha=$(git ls-remote "$url" "refs/heads/$branch" | cut -f1)
+    echo "$name SHA for branch $branch: ${sha:-"Not Found"}"
+}
+get_sha "sglang" "$SGLANG_URL" "$SGLANG_BRANCH"
+get_sha "sgl-kernel" "$SGL_KERNEL_URL" "$SGL_KERNEL_BRANCH"
+chmod +x scripts/ci/npu/npu_log_print.sh