Use rapids-pip-retry in CI jobs that might need retries (#125)

Uses a retry wrapper for `pip` commands to try to alleviate CI failures due to hash mismatches that result from network hiccups xref rapidsai/build-planning#148 This will retry failures that show up in CI like: ``` Collecting nvidia-cublas-cu12 (from libraft-cu12==25.2.*,>=0.0.0a0) Downloading https://pypi.nvidia.com/nvidia-cublas-cu12/nvidia_cublas_cu12-12.8.3.14-py3-none-manylinux_2_27_aarch64.whl (604.9 MB) ━━━━━━━━━━━━━━━━━━━━━ 350.2/604.9 MB 229.2 MB/s eta 0:00:02 ERROR: THESE PACKAGES DO NOT MATCH THE HASHES FROM THE REQUIREMENTS FILE. If you have updated the package versions, please update the hashes. Otherwise, examine the package contents carefully; someone may have tampered with them. nvidia-cublas-cu12 from https://pypi.nvidia.com/nvidia-cublas-cu12/nvidia_cublas_cu12-12.8.3.14-py3-none-manylinux_2_27_aarch64.whl#sha256=93a4e0e386cc7f6e56c822531396de8170ed17068a1e18f987574895044cd8c3 (from libraft-cu12==25.2.*,>=0.0.0a0): Expected sha256 93a4e0e386cc7f6e56c822531396de8170ed17068a1e18f987574895044cd8c3 Got 849c88d155cb4b4a3fdfebff9270fb367c58370b4243a2bdbcb1b9e7e940b7be ``` This PR also updates the build images used for `ci-wheel` to use CUDA 12.8.0 (we no longer maintain CUDA 12.0.1 build images) and uses NVKS L4 GPUs for amd64 testing, to help move us off of the old CI cluster. --------- Co-authored-by: Bradley Dice <[email protected]>
rapidsai · Feb 25, 2025 · 5e37811 · 5e37811
1 parent 68e63ae
commit 5e37811
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 11 deletions.
diff --git a/.github/actions/compute-matrix/action.yaml b/.github/actions/compute-matrix/action.yaml
@@ -16,18 +16,18 @@ runs:
         set -eo pipefail
 
         export BUILD_MATRIX="
-        - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.10', LINUX_VER: 'rockylinux8' }
-        - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.11', LINUX_VER: 'rockylinux8' }
-        - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.12', LINUX_VER: 'rockylinux8' }
-        - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.10', LINUX_VER: 'rockylinux8' }
-        - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.11', LINUX_VER: 'rockylinux8' }
-        - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.12', LINUX_VER: 'rockylinux8' }
+        - { CUDA_VER: '12.8.0', ARCH: 'amd64', PY_VER: '3.10', LINUX_VER: 'rockylinux8' }
+        - { CUDA_VER: '12.8.0', ARCH: 'amd64', PY_VER: '3.11', LINUX_VER: 'rockylinux8' }
+        - { CUDA_VER: '12.8.0', ARCH: 'amd64', PY_VER: '3.12', LINUX_VER: 'rockylinux8' }
+        - { CUDA_VER: '12.8.0', ARCH: 'arm64', PY_VER: '3.10', LINUX_VER: 'rockylinux8' }
+        - { CUDA_VER: '12.8.0', ARCH: 'arm64', PY_VER: '3.11', LINUX_VER: 'rockylinux8' }
+        - { CUDA_VER: '12.8.0', ARCH: 'arm64', PY_VER: '3.12', LINUX_VER: 'rockylinux8' }
         "
 
         export TEST_MATRIX="
-          - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.10', LINUX_VER: 'ubuntu20.04', gpu: 'v100', driver: 'latest' }
-          - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.11', LINUX_VER: 'ubuntu20.04', gpu: 'v100', driver: 'latest' }
-          - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.12', LINUX_VER: 'ubuntu20.04', gpu: 'v100', driver: 'latest' }
+          - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.10', LINUX_VER: 'ubuntu20.04', gpu: 'l4',   driver: 'latest' }
+          - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.11', LINUX_VER: 'ubuntu20.04', gpu: 'l4',   driver: 'latest' }
+          - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.12', LINUX_VER: 'ubuntu20.04', gpu: 'l4',   driver: 'latest' }
           - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.10', LINUX_VER: 'ubuntu20.04', gpu: 'a100', driver: 'latest' }
           - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.11', LINUX_VER: 'ubuntu20.04', gpu: 'a100', driver: 'latest' }
           - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.12', LINUX_VER: 'ubuntu20.04', gpu: 'a100', driver: 'latest' }

diff --git a/ci/build_wheel.sh b/ci/build_wheel.sh
@@ -14,7 +14,7 @@ sccache --zero-stats
 
 rapids-logger "Build wheel"
 mkdir -p ./dist
-python -m pip wheel . --wheel-dir=./dist -v --disable-pip-version-check --no-deps
+rapids-pip-retry wheel . --wheel-dir=./dist -v --disable-pip-version-check --no-deps
 
 sccache --show-adv-stats
 

diff --git a/ci/test_wheel.sh b/ci/test_wheel.sh
@@ -11,7 +11,7 @@ RAPIDS_TESTS_DIR=${RAPIDS_TESTS_DIR:-"${PWD}/test-results"}/
 mkdir -p "${RAPIDS_TESTS_DIR}"
 
 rapids-logger "Install wheel"
-python -m pip install "$(echo ./dist/pynvjitlink_"${RAPIDS_PY_CUDA_SUFFIX}"*.whl)[test]"
+rapids-pip-retry install "$(echo ./dist/pynvjitlink_"${RAPIDS_PY_CUDA_SUFFIX}"*.whl)[test]"
 
 rapids-logger "Build Tests"
 pushd test_binary_generation