This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 0ec36587af [CI] Updated cibw to 4.1.0 (#19754)
0ec36587af is described below
commit 0ec36587afb307c35c4e734af3a73c7c8f95f649
Author: Shushi Hong <[email protected]>
AuthorDate: Sat Jun 13 07:28:20 2026 -0400
[CI] Updated cibw to 4.1.0 (#19754)
This pr follows the cibuildwheel 4.0 announcement, the official prebuilt
quay.io/manylinux_cuda images ship the CUDA toolkit preinstalled under
/usr/local/cuda on the same manylinux_2_28 baseline the wheel targets.
also switchs the Linux build_cuda_runtime sidecar legs to
quay.io/manylinux_cuda/manylinux_2_28_{x86_64,aarch64}_cuda13_1 and drop
the per-run NVIDIA local-repo RPM download plus dnf install of the
toolkit, which pulled several GB from developer.download.nvidia.com on
every run and was the main source of sidecar build-time variance. This
moves the Linux sidecar from CUDA 13.0.2 to 13.1; the soname stays
libcudart.so.13, so the repair-step glob excludes (libcudart.so.*) are
unaffected and the sidecar carries no device code. The Windows sidecar
keeps using conda and is unchanged.
---
.github/actions/build-wheel-for-publish/action.yml | 2 +-
.github/workflows/publish_wheel.yml | 9 ++++----
.../package/manylinux_build_libtvm_runtime_cuda.sh | 24 +++++++---------------
3 files changed, 13 insertions(+), 22 deletions(-)
diff --git a/.github/actions/build-wheel-for-publish/action.yml
b/.github/actions/build-wheel-for-publish/action.yml
index 44903aeaa8..e718442379 100644
--- a/.github/actions/build-wheel-for-publish/action.yml
+++ b/.github/actions/build-wheel-for-publish/action.yml
@@ -108,7 +108,7 @@ runs:
# ---- Build and test wheels ----
- name: Build and test wheels
- uses: pypa/[email protected]
+ uses: pypa/[email protected]
with:
package-dir: .
output-dir: wheelhouse
diff --git a/.github/workflows/publish_wheel.yml
b/.github/workflows/publish_wheel.yml
index 5865e12440..63375e6063 100644
--- a/.github/workflows/publish_wheel.yml
+++ b/.github/workflows/publish_wheel.yml
@@ -44,8 +44,9 @@ env:
jobs:
# Build the CUDA runtime sidecar once per arch and upload it as an artifact
that
- # build_wheels bundles. The Linux legs build inside a manylinux_2_28 image
-- the
- # same glibc baseline cibuildwheel targets for the wheel -- so the sidecar
stays
+ # build_wheels bundles. The Linux legs build inside the official
manylinux_2_28
+ # CUDA image (CUDA toolkit preinstalled, see pypa/manylinux) -- the same
glibc
+ # baseline cibuildwheel targets for the wheel -- so the sidecar stays
# ABI-compatible with the wheel's libtvm_runtime.so regardless of the exact
tag.
build_cuda_runtime:
name: ${{ matrix.name }}
@@ -57,13 +58,13 @@ jobs:
include:
- name: "CUDA runtime sidecar (Linux x86_64, manylinux_2_28)"
os: ubuntu-latest
- container: quay.io/pypa/manylinux_2_28_x86_64:latest
+ container:
quay.io/manylinux_cuda/manylinux_2_28_x86_64_cuda13_1:latest
arch: x86_64
script: ci/scripts/package/manylinux_build_libtvm_runtime_cuda.sh
lib: build-wheel-cuda/lib/libtvm_runtime_cuda.so
- name: "CUDA runtime sidecar (Linux aarch64, manylinux_2_28)"
os: ubuntu-24.04-arm
- container: quay.io/pypa/manylinux_2_28_aarch64:latest
+ container:
quay.io/manylinux_cuda/manylinux_2_28_aarch64_cuda13_1:latest
arch: aarch64
script: ci/scripts/package/manylinux_build_libtvm_runtime_cuda.sh
lib: build-wheel-cuda/lib/libtvm_runtime_cuda.so
diff --git a/ci/scripts/package/manylinux_build_libtvm_runtime_cuda.sh
b/ci/scripts/package/manylinux_build_libtvm_runtime_cuda.sh
index fe721a18f4..66e3d787b4 100755
--- a/ci/scripts/package/manylinux_build_libtvm_runtime_cuda.sh
+++ b/ci/scripts/package/manylinux_build_libtvm_runtime_cuda.sh
@@ -16,9 +16,11 @@
# specific language governing permissions and limitations
# under the License.
#
-# Build libtvm_runtime_cuda.so inside a manylinux container, run by the
-# build_cuda_runtime CI job. Installs the pinned CUDA toolkit and builds the
-# sidecar into build-wheel-cuda/lib/ for the wheel build to bundle.
+# Build libtvm_runtime_cuda.so inside a manylinux CUDA container, run by the
+# build_cuda_runtime CI job. The official quay.io/manylinux_cuda images ship
+# the CUDA toolkit preinstalled under /usr/local/cuda, so no toolkit install
+# is needed here. Builds the sidecar into build-wheel-cuda/lib/ for the wheel
+# build to bundle.
#
# Usage: manylinux_build_libtvm_runtime_cuda.sh
set -euxo pipefail
@@ -28,21 +30,9 @@ build_dir="${repo_root}/build-wheel-cuda"
python_bin="/opt/python/cp310-cp310/bin/python"
parallel="$(getconf _NPROCESSORS_ONLN 2>/dev/null || echo 4)"
-# Install the pinned CUDA toolkit into the manylinux_2_28 container. The RHEL8
-# local-repo RPM is compatible with manylinux_2_28 for both x86_64 and aarch64.
-arch="$(uname -m)"
-cuda_rpm="cuda-repo-rhel8-13-0-local-13.0.2_580.95.05-1.${arch}.rpm"
-curl -fsSLo "/tmp/${cuda_rpm}" \
-
"https://developer.download.nvidia.com/compute/cuda/13.0.2/local_installers/${cuda_rpm}";
-rpm -i "/tmp/${cuda_rpm}"
-dnf clean all
-dnf -y --disablerepo=epel install cuda-toolkit-13-0
-rm -f "/tmp/${cuda_rpm}"
-dnf clean all
-
# Build the CUDA runtime sidecar with CUDA on and LLVM off, so it does not need
-# the LLVM prefix; the main CPU wheel links LLVM statically. The manylinux
image
-# ships no cmake/ninja, so install the build tools here.
+# the LLVM prefix; the main CPU wheel links LLVM statically. pip-install
+# cmake/ninja rather than relying on whatever the image ships.
export PATH="/opt/python/cp310-cp310/bin:/usr/local/cuda/bin:${PATH}"
"${python_bin}" -m pip install -U pip cmake ninja
nvcc --version
