Skip to content

Commit c016d65

Browse files
leofangvzhurba01rwgkrobertmaynard
authored
Update cuda.bindings to 13.0.0 (#792)
* Propagate generated path finder changes * Rebase to 13.0 RC14 * Update license headers on examples * Regenerate after merging upstream * Update benchmarks and run pre-commit * cython-gen output, NO manual changes * Bump cuda/bindings/_version.py → 13.0.0 * `path_finder` and cybind updates for CTK 13.0 (#81) * Update SUPPORTED_WINDOWS_DLLS: kitpicks/cuda-r13-0/13.0.0/013/local_installers/cuda_13.0.0_windows.exe * Update SUPPORTED_LINUX_SONAMES: kitpicks/cuda-r13-0/13.0.0/013/local_installers/cuda_13.0.0_580.31_linux.run * 013 → 014: SUPPORTED_LINUX_SONAMES unchanged * 013 → 014: SUPPORTED_WINDOWS_DLLS unchanged * cybind update with 13.0.0 headers (014) * Bump cuda/bindings/_version.py → 13.0.0 * test_nvjitlink.py: remove sm_60, add sm_100 * Updates from cybind after removing all 11.x headers (affects "automatically generated" comments only). * Add new toolshed/reformat_cuda_enums_as_py.py (reads cuda.h, driver_types.h headers directly). * Use new toolshed/reformat_cuda_enums_as_py.py to regenerate driver_cu_result_explanations.py, runtime_cuda_error_explanations.py * Use `driver.cuDeviceGetUuid()` instead of `driver.cuDeviceGetUuid_v2()` with CTK 13. * Adjustments for locating nvvm directory in CTK 13 installations. * Fixes from windows testing (#89) * Add missing error handling (tests/test_nvjitlink.py) * Add missing `const` in cudaMemcpyBatchAsync call (cuda/bindings/runtime.pyx.in) * Add qa/13.0.0/01_linux.sh * Remove qa/13.0.0/01_linux.sh after it was moved to a new upstream qa branch. * Strictly correct casts for cudaMemcpyBatchAsync (generated by cython_gen). * Pragmatic minimal fix for cudaMemcpyBatchAsync casts (works with Linux and Windows). (generated with cython-gen) * print *prog pointers in nvrtcCreateProgram, nvrtcCompileProgram bindings * Remove stray `"nvrtc64_*_0.alt.dll"` entries in `SUPPORTED_WINDOWS_DLLS` * Revert "print *prog pointers in nvrtcCreateProgram, nvrtcCompileProgram bindings" This reverts commit 104abbd. * _find_lib_dir_using_cuda_home(): Windows CTK 13 → bin\x64 * getLocalRuntimeVersion(): Search for libcudart.so.13 * SUPPORTED_LINUX_SONAMES: Add CTK 13 soname values * Update path_finder/supported_libs.py from kitpicks 13.0.0/025 (#96) * Linux update from cuda_13.0.0_580.46_kitpicks025_linux.run: no-op b/o NVIDIA/cuda-python-private#95 * Windows update from cuda_13.0.0_kitpicks025_windows.exe * This trivial change should have been included in PR #81, but was overlooked. Direct commit for simplicity. * cuda_core forward compatibility changes (private development branch) (#94) * CCCL_INCLUDE_PATH fixes in test_event.py, test_launcher.py * Add new file (accidentally missing in a prior commit). * Fix pre-commit errors in new tests/helpers.py * 12→13 compatibility fixes in cuda/core/experimental/_graph.py * CTK 12 compatibility (tests/test_cuda_utils.py) * Make the cuda/core/experimental/_graph.py changes backwards compatible. * Do not try to hide `13` in cuda_core/tests/test_cuda_utils.py * More elegant handling of `CCCL_INCLUDE_PATHS` in cuda_core/tests/helpers.py * Remove stray empty line (cuda_core/tests/conftest.py). * Fix logic error computing CCCL_INCLUDE_PATHS in cuda_core/tests/helpers.py * Fix `cuda_bindings` and `cuda_core` examples (#98) * Unmask globalToShmemAsyncCopy_test.py error: explicit pytest_skipif_cuda_include_not_found(), pytest_skipif_compute_capability_too_low() * Update cuda_bindings/examples/common/common.py for CTK 13 compatibility, to fix globalToShmemAsyncCopy_test.py * Update cuda_core/examples/thread_block_cluster.py for CTK 13 compatibility. * Update driver_cu_result_explanations.py, runtime_cuda_error_explanations.py (#100) * kitpicks/cuda-r13-0/13.0.0/033: CUDA_HOME=/usr/local/cuda python cython_gen.py --target-lib driver runtime nvrtc --out ../unreleased-13.0 (#107) * Update cuda_pathfinder supported_nvidia_libs.py from kitpicks 13.0.0/036 (NO CHANGES compared to 025) * Update driver_cu_result_explanations.py, runtime_cuda_error_explanations.py from kitpicks 13.0.0/036 (NO CHANGES compared to 025) * Update cuda_pathfinder supported_nvidia_libs.py EXPECTED_LIB_SYMBOLS for libnpp* The newly chosen symbols appear in all CTK 12.x releases and 13.0.0: https://gitlab-master.nvidia.com/rgrossekunst/rwgk_config_nvidia/-/blob/a1c2f29decd9b93fc7af9611bdc60565446b0cd3/bin/check_libnpp_symbols.sh * cython-gen changes due to PR #101 (#115) * cython-gen changes due to release_gil_revert_leos_commits_fix_cast_error (#116) * cython-gen changes due to cython-gen PR #118 (#120) * test_cufile.py: pytest.skip("NEEDS DEBUGGING (unreleased-13.0)") * cython-gen changes on top of `git merge world-main -X ours` product. * Add missing imports (related to #769). These got lost due to merging with `-X ours` * Revert obsolete aec7d10 Made obsolete by #778 * Remove cuda_bindings/site-packages entirely. * Change test_batch_io_large_operations to avoid a flood of output (`assert read_data == expected_data` failure). * Remove `(scope="module")` from `cufile_env_json` fixture: resolves test_batch_io_large_operations failure. * [unreleased-13.0] `test_cufile.py`: Remove fallback to `/etc/cufile.json` (#126) * test_cufile.py: NEVER USE /etc/cufile.json * Remove /etc/cufile.json code entirely. * update win driver to 580.88 * change backport branch to 12.9.x * update build ver to 13.0.0 * crt headers are now split from cudart (or nvcc?) * remove the outdated cufile skip condition (it was buggy anyway) * remove 11.8 CI and add 13.0 CI * update cuda-bindings optional dependencies * update release notes * update cuda-bindings docs * update cuda-python docs * libnvvm is also split out * ensure using sanitizer from the latest release of the same major ver * Remove -cu12 suffixes and add nvidia-nvvm in cuda_pathfinder/pyproject.toml. Make related changes in .github/workflows * fix backport branch's ci name * restore nvidia_wheels_cu12 * remove tests * always test 12.9.x with the latest driver * ensure fetch_ctk works with 12.x * Fix Linux libnvvm site-packages search for CTK 13 CTK 12: site-packages/nvidia/cuda_nvcc/nvvm/lib64/libnvvm.so CTK 13: site-packages/nvidia/cu13/lib/libnvvm.so.4 * update docs * add PTX ISA 9.0 to utils * sync 13.0.0 docs * Fix Windows site-packages search for CTK 13 * Also add "nvidia-nvvm~=13.0" in cuda_bindings/pyproject.toml * Add _work_around_known_bugs() in load_dl_linux.py To resolve this issue: #792 (comment) * driver_cu_result_explanations.py, runtime_cuda_error_explanations.py refresh (no-op) * SUPPORTED_LINUX_SONAMES refresh (no-op) * SUPPORTED_WINDOWS_DLLS refresh (no-op) * Update generated files: nvjitlink, nvvm (trivial changes, functional no-op) * update release dates --------- Co-authored-by: Vladislav Zhurba <[email protected]> Co-authored-by: Vladislav Zhurba <[email protected]> Co-authored-by: Ralf W. Grosse-Kunstleve <[email protected]> Co-authored-by: Ralf W. Grosse-Kunstleve <[email protected]> Co-authored-by: Robert Maynard <[email protected]>
1 parent 926b4e6 commit c016d65

File tree

110 files changed

+6513
-6959
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

110 files changed

+6513
-6959
lines changed

‎.github/BACKPORT_BRANCH

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
11.8.x
1+
12.9.x

‎.github/actions/fetch_ctk/action.yml

Lines changed: 7 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ inputs:
1717
description: "A list of the CTK components to install as a comma-separated list. e.g. 'cuda_nvcc,cuda_nvrtc,cuda_cudart'"
1818
required: false
1919
type: string
20-
default: "cuda_nvcc,cuda_cudart,cuda_nvrtc,cuda_profiler_api,cuda_cccl,libnvjitlink,libcufile"
20+
default: "cuda_nvcc,cuda_cudart,cuda_crt,libnvvm,cuda_nvrtc,cuda_profiler_api,cuda_cccl,libnvjitlink,libcufile"
2121

2222
runs:
2323
using: composite
@@ -32,15 +32,16 @@ runs:
3232
if [[ "$CUDA_MAJOR_VER" -lt 12 ]]; then
3333
CTK_CACHE_COMPONENTS="${CTK_CACHE_COMPONENTS//libnvjitlink/}"
3434
fi
35+
# Conditionally strip out cuda_crt and libnvvm for CUDA versions < 13
36+
CUDA_MAJOR_VER="$(cut -d '.' -f 1 <<< ${{ inputs.cuda-version }})"
37+
if [[ "$CUDA_MAJOR_VER" -lt 13 ]]; then
38+
CTK_CACHE_COMPONENTS="${CTK_CACHE_COMPONENTS//cuda_crt/}"
39+
CTK_CACHE_COMPONENTS="${CTK_CACHE_COMPONENTS//libnvvm/}"
40+
fi
3541
# Conditionally strip out libcufile since it does not support Windows
3642
if [[ "${{ inputs.host-platform }}" == win-* ]]; then
3743
CTK_CACHE_COMPONENTS="${CTK_CACHE_COMPONENTS//libcufile/}"
3844
fi
39-
# Conditionally strip out libcufile for CUDA versions < 12.2.0 + aarch64 (redist not available)
40-
CUDA_MINOR_VER="$(cut -d '.' -f 2 <<< ${{ inputs.cuda-version }})"
41-
if [[ ("$CUDA_MAJOR_VER" -lt 12 || "$CUDA_MINOR_VER" -lt 2) && "${{ inputs.host-platform }}" == "linux-aarch64" ]]; then
42-
CTK_CACHE_COMPONENTS="${CTK_CACHE_COMPONENTS//libcufile/}"
43-
fi
4445
# Cleanup stray commas after removing components
4546
CTK_CACHE_COMPONENTS="${CTK_CACHE_COMPONENTS//,,/,}"
4647

‎.github/workflows/guess_latest.sh

Lines changed: 11 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,18 +6,27 @@
66
# URL to search
77
URL="https://developer.download.nvidia.com/compute/cuda/redist/"
88

9+
# Ensure exactly one argument is provided
10+
if [ "$#" -ne 1 ]; then
11+
echo "Usage: $0 <CUDA_major_version>"
12+
exit 1
13+
fi
14+
15+
# Accept major version as the first argument
16+
MAJOR_VERSION="$1"
17+
918
# Fetch the directory listing and extract the latest version number
1019
get_latest_version() {
1120
# Get the HTML content of the page
1221
local html_content=$(wget -q -O - "$URL")
1322

1423
# Extract links matching the pattern redistrib_?.?.?.json
15-
local files=$(echo "$html_content" | grep -oP 'redistrib_[0-9]+\.[0-9]+\.[0-9]+\.json' | cut -d'"' -f2)
24+
local files=$(echo "$html_content" | grep -oP "redistrib_${MAJOR_VERSION}\.[0-9]+\.[0-9]+\.json" | cut -d'"' -f2)
1625

1726
# If files were found, extract the version numbers and find the latest
1827
if [ -n "$files" ]; then
1928
# Extract just the version numbers using regex
20-
local versions=$(echo "$files" | grep -oP 'redistrib_\K[0-9]+\.[0-9]+\.[0-9]+(?=\.json)')
29+
local versions=$(echo "$files" | grep -oP "redistrib_\K${MAJOR_VERSION}\.[0-9]+\.[0-9]+(?=\.json)")
2130

2231
# Sort the versions and get the latest
2332
local latest_version=$(echo "$versions" | sort -V | tail -n 1)

‎.github/workflows/install_gpu_driver.ps1

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,9 +6,9 @@
66
function Install-Driver {
77

88
# Set the correct URL, filename, and arguments to the installer
9-
# This driver is picked to support Windows 11 & CUDA 12.8
10-
$url = 'https://us.download.nvidia.com/tesla/572.13/572.13-data-center-tesla-desktop-win10-win11-64bit-dch-international.exe';
11-
$file_dir = 'C:\NVIDIA-Driver\572.13-data-center-tesla-desktop-win10-win11-64bit-dch-international.exe';
9+
# This driver is picked to support Windows 11 & CUDA 13.0
10+
$url = 'https://us.download.nvidia.com/tesla/580.88/580.88-data-center-tesla-desktop-win10-win11-64bit-dch-international.exe';
11+
$file_dir = 'C:\NVIDIA-Driver\580.88-data-center-tesla-desktop-win10-win11-64bit-dch-international.exe';
1212
$install_args = '/s /noeula /noreboot';
1313

1414
# Create the folder for the driver download

‎.github/workflows/test-wheel-linux.yml

Lines changed: 12 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,7 @@ jobs:
5151
# Add a special entry for the H100 runner on amd64.
5252
special_runner=""
5353
if [[ "${ARCH}" == "amd64" ]]; then
54-
special_runner="- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: 'H100', DRIVER: 'latest' }"
54+
special_runner="- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: 'H100', DRIVER: 'latest' }"
5555
fi
5656
5757
# Please keep the matrices sorted in ascending order by the following:
@@ -62,18 +62,16 @@ jobs:
6262
#
6363
export MATRICES="
6464
pull-request:
65-
- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }
66-
- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
6765
- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }
68-
- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'earliest' }
66+
- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
6967
- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
70-
- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
68+
- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '13.0.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }
7169
- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }
72-
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'earliest' }
70+
- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
7371
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
74-
- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }
75-
- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
72+
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '13.0.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }
7673
- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }
74+
- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }
7775
${special_runner}
7876
nightly:
7977
- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }
@@ -200,13 +198,14 @@ jobs:
200198
201199
OLD_BRANCH=$(cat .github/BACKPORT_BRANCH)
202200
OLD_BASENAME="cuda-bindings-python${PYTHON_VERSION_FORMATTED}-cuda*-${{ inputs.host-platform }}*"
203-
LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "build-and-test.yml" -s completed -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')
201+
LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "ci.yml" -s completed -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')
204202
if [[ "$LATEST_PRIOR_RUN_ID" == "" ]]; then
205203
echo "LATEST_PRIOR_RUN_ID not found!"
206204
exit 1
207205
fi
208206
209207
gh run download $LATEST_PRIOR_RUN_ID -p ${OLD_BASENAME} -R NVIDIA/cuda-python
208+
rm -rf ${OLD_BASENAME}-tests # exclude cython test artifacts
210209
ls -al $OLD_BASENAME
211210
mkdir -p "${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}"
212211
mv $OLD_BASENAME/*.whl "${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}"/
@@ -318,16 +317,16 @@ jobs:
318317
pip install $(ls cuda_python*.whl)[all]
319318
fi
320319
321-
- name: Install cuda.pathfinder nvidia_wheels_cu12
322-
if: startsWith(matrix.CUDA_VER, '12.')
320+
- name: Install cuda.pathfinder nvidia_wheels_cu13
321+
if: startsWith(matrix.CUDA_VER, '13.')
323322
run: |
324323
pushd cuda_pathfinder
325-
pip install -v .[nvidia_wheels_cu12]
324+
pip install -v .[nvidia_wheels_cu13]
326325
pip freeze
327326
popd
328327
329328
- name: Run cuda.pathfinder tests with all_must_work
330-
if: startsWith(matrix.CUDA_VER, '12.')
329+
if: startsWith(matrix.CUDA_VER, '13.')
331330
env:
332331
CUDA_PATHFINDER_TEST_LOAD_NVIDIA_DYNAMIC_LIB_STRICTNESS: all_must_work
333332
run: run-tests pathfinder

‎.github/workflows/test-wheel-windows.yml

Lines changed: 8 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -47,10 +47,10 @@ jobs:
4747
#
4848
export MATRICES="
4949
pull-request:
50-
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '11.8.0', LOCAL_CTK: '0' }
51-
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '11.8.0', LOCAL_CTK: '1' }
5250
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.9.0', LOCAL_CTK: '0' }
5351
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.9.0', LOCAL_CTK: '1' }
52+
- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '13.0.0', LOCAL_CTK: '0' }
53+
- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '13.0.0', LOCAL_CTK: '1' }
5454
nightly:
5555
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '11.8.0', LOCAL_CTK: '0' }
5656
- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '11.8.0', LOCAL_CTK: '1' }
@@ -178,14 +178,15 @@ jobs:
178178
run: |
179179
$OLD_BRANCH = Get-Content .github/BACKPORT_BRANCH
180180
$OLD_BASENAME = "cuda-bindings-python${env:PYTHON_VERSION_FORMATTED}-cuda*-${{ inputs.host-platform }}*"
181-
$runData = gh run list -b $OLD_BRANCH -L 1 -w "build-and-test.yml" -s completed -R NVIDIA/cuda-python --json databaseId | ConvertFrom-Json
181+
$runData = gh run list -b $OLD_BRANCH -L 1 -w "ci.yml" -s completed -R NVIDIA/cuda-python --json databaseId | ConvertFrom-Json
182182
if (-not $runData -or $runData.Length -eq 0 -or -not $runData[0].databaseId -or [string]::IsNullOrEmpty($runData[0].databaseId)) {
183183
Write-Host "LATEST_PRIOR_RUN_ID not found!"
184184
exit 1
185185
}
186186
$LATEST_PRIOR_RUN_ID = $runData[0].databaseId
187187
188188
gh run download $LATEST_PRIOR_RUN_ID -p $OLD_BASENAME -R NVIDIA/cuda-python
189+
Remove-Item -Recurse -Force "${OLD_BASENAME}-tests" # exclude cython test artifacts
189190
Get-ChildItem -Path $OLD_BASENAME
190191
New-Item -Path "${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}" -ItemType Directory -Force
191192
Move-Item -Path "$OLD_BASENAME/*.whl" -Destination "${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}"
@@ -285,17 +286,17 @@ jobs:
285286
pip install "$((Get-ChildItem -Filter cuda_python*.whl).FullName)[all]"
286287
}
287288
288-
- name: Install cuda.pathfinder nvidia_wheels_cu12
289-
if: startsWith(matrix.CUDA_VER, '12.')
289+
- name: Install cuda.pathfinder nvidia_wheels_cu13
290+
if: startsWith(matrix.CUDA_VER, '13.')
290291
shell: bash --noprofile --norc -xeuo pipefail {0}
291292
run: |
292293
pushd cuda_pathfinder
293-
pip install -v .[nvidia_wheels_cu12]
294+
pip install -v .[nvidia_wheels_cu13]
294295
pip freeze
295296
popd
296297
297298
- name: Run cuda.pathfinder tests with all_must_work
298-
if: startsWith(matrix.CUDA_VER, '12.')
299+
if: startsWith(matrix.CUDA_VER, '13.')
299300
env:
300301
CUDA_PATHFINDER_TEST_LOAD_NVIDIA_DYNAMIC_LIB_STRICTNESS: all_must_work
301302
shell: bash --noprofile --norc -xeuo pipefail {0}

‎README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -38,3 +38,4 @@ The list of available interfaces is:
3838
* NVRTC
3939
* nvJitLink
4040
* NVVM
41+
* cuFile

‎ci/tools/env-vars

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -60,7 +60,7 @@ elif [[ "${1}" == "test" ]]; then
6060
# We only test compute-sanitizer on python 3.12 arbitrarily; we don't need to use sanitizer on the entire matrix
6161
# Only local ctk installs have compute-sanitizer; there is no wheel for it
6262
if [[ "${PY_VER}" == "3.12" && "${CUDA_VER}" != "11.8.0" && "${LOCAL_CTK}" == 1 && "${HOST_PLATFORM}" == linux* ]]; then
63-
echo "LATEST_CUDA_VERSION=$(bash .github/workflows/guess_latest.sh)" >> $GITHUB_ENV
63+
echo "LATEST_CUDA_VERSION=$(bash .github/workflows/guess_latest.sh $TEST_CUDA_MAJOR)" >> $GITHUB_ENV
6464
SETUP_SANITIZER=1
6565
else
6666
SETUP_SANITIZER=0

‎ci/versions.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
{
22
"cuda": {
33
"build": {
4-
"version": "12.9.0"
4+
"version": "13.0.0"
55
}
66
}
77
}

‎cuda_bindings/benchmarks/conftest.py

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,9 @@
44
import numpy as np
55
import pytest
66

7-
from cuda import cuda, cudart, nvrtc
7+
from cuda.bindings import driver as cuda
8+
from cuda.bindings import nvrtc
9+
from cuda.bindings import runtime as cudart
810

911

1012
def ASSERT_DRV(err):
@@ -28,7 +30,7 @@ def init_cuda():
2830
ASSERT_DRV(err)
2931
err, device = cuda.cuDeviceGet(0)
3032
ASSERT_DRV(err)
31-
err, ctx = cuda.cuCtxCreate(0, device)
33+
err, ctx = cuda.cuCtxCreate(None, 0, device)
3234
ASSERT_DRV(err)
3335

3436
# create stream

0 commit comments

Comments
 (0)