Skip to content

Commit 52a829d

Browse files
saudetsaudet
committed
* Upgrade presets for MKL 2025.0, LLVM 19.1.3, nvCOMP 4.1.0.6, PyTorch 2.5.1, Triton Inference Server 2.51.0
1 parent ba960fc commit 52a829d

File tree

64 files changed

+992
-414
lines changed

Some content is hidden

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

64 files changed

+992
-414
lines changed

‎.github/actions/deploy-ubuntu/action.yml

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ runs:
4444
export CUDA=cuda-repo-rhel8-12-6-local-12.6.2_560.35.03-1.aarch64.rpm
4545
export CUDNN=cuda-12-9.5.1.17-1.aarch64
4646
export NCCL=2.23.4-1+cuda12.6.aarch64
47-
export NVCOMP=nvcomp-linux-sbsa-4.0.1-cuda12.x
47+
export NVCOMP=nvcomp-linux-sbsa-4.1.0.6_cuda12-archive
4848
export USERLAND_BUILDME="buildme --aarch64"
4949
elif [[ "$CI_DEPLOY_PLATFORM" == "linux-ppc64le" ]]; then
5050
export ARCH=ppc64el
@@ -66,7 +66,7 @@ runs:
6666
export CUDA=cuda-repo-rhel8-12-6-local-12.6.2_560.35.03-1.x86_64.rpm
6767
export CUDNN=cuda-12-9.5.1.17-1.x86_64
6868
export NCCL=2.23.4-1+cuda12.6.x86_64
69-
export NVCOMP=nvcomp-linux-x86_64-4.0.1-cuda12.x
69+
export NVCOMP=nvcomp-linux-x86_64-4.1.0.6_cuda12-archive
7070
fi
7171
echo "ARCH=$ARCH" >> $GITHUB_ENV
7272
echo "PREFIX=$PREFIX" >> $GITHUB_ENV
@@ -183,9 +183,9 @@ runs:
183183
for f in /usr/local/cuda/lib64/libcudnn*so.9.*; do $SUDO ln -sf $f ${f:0:${#f}-4}; $SUDO ln -sf $f ${f:0:${#f}-6}; done
184184
185185
if [[ -n ${NVCOMP:-} ]]; then
186-
curl -LO https://developer.download.nvidia.com/compute/nvcomp/4.0.1/local_installers/$NVCOMP.tar.gz
187-
$SUDO tar -xvf $NVCOMP.tar.gz -C /usr/local/cuda/lib64/ --strip-components=1 lib/ || $SUDO tar -xvf $NVCOMP.tar.gz -C /usr/local/cuda/lib64/ --strip-components=2 nvcomp/lib/
188-
$SUDO tar -xvf $NVCOMP.tar.gz -C /usr/local/cuda/include/ --strip-components=1 include/ || $SUDO tar -xvf $NVCOMP.tar.gz -C /usr/local/cuda/include/ --strip-components=2 nvcomp/include/
186+
curl -LO https://developer.download.nvidia.com/compute/nvcomp/redist/nvcomp/linux-$ARCH_CUDA/$NVCOMP.tar.xz
187+
$SUDO tar -xvf $NVCOMP.tar.xz -C /usr/local/cuda/lib64/ --strip-components=2 */lib/
188+
$SUDO tar -xvf $NVCOMP.tar.xz -C /usr/local/cuda/include/ --strip-components=2 */include/
189189
rm -f $NVCOMP.tar.gz
190190
fi
191191
@@ -228,8 +228,8 @@ runs:
228228
229229
if [[ "$CI_DEPLOY_MODULE" == "mkl" ]]; then
230230
echo Installing MKL
231-
curl -LO https://registrationcenter-download.intel.com/akdlm/IRC_NAS/89a381f6-f85d-4dda-ae62-30d51470f53c/l_onemkl_p_2024.2.2.17_offline.sh
232-
$SUDO bash l_onemkl_p_2024.2.2.17_offline.sh -s -a -s --eula accept
231+
curl -LO https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940_offline.sh
232+
$SUDO bash intel-onemkl-2025.0.0.940_offline.sh -s -a -s --eula accept
233233
export MAVEN_OPTIONS="-Djavacpp.platform.compiler=clang++"
234234
fi
235235

‎.github/actions/deploy-windows/action.yml

Lines changed: 8 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -102,7 +102,7 @@ runs:
102102
curl -LO https://developer.download.nvidia.com/compute/cuda/12.6.2/local_installers/cuda_12.6.2_560.94_windows.exe
103103
curl -LO https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/cudnn-windows-x86_64-9.5.1.17_cuda12-archive.zip
104104
curl -LO http://www.winimage.com/zLibDll/zlib123dllx64.zip
105-
curl -LO https://developer.download.nvidia.com/compute/nvcomp/4.0.1/local_installers/nvcomp-windows-x86_64-4.0.1-cuda12.x.zip
105+
curl -LO https://developer.download.nvidia.com/compute/nvcomp/redist/nvcomp/windows-x86_64/nvcomp-windows-x86_64-4.1.0.6_cuda12-archive.zip
106106
cuda_11.8.0_522.06_windows.exe -s
107107
bash -c "rm -Rf 'C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.8'"
108108
bash -c "mv 'C:/Program Files/NVIDIA Corporation/NvToolsExt' 'C:/Program Files/NVIDIA Corporation/NvToolsExt_old'"
@@ -111,17 +111,15 @@ runs:
111111
bash -c "ls 'C:/Program Files/NVIDIA Corporation/NvToolsExt'"
112112
unzip cudnn-windows-x86_64-9.5.1.17_cuda12-archive.zip
113113
unzip zlib123dllx64.zip
114-
unzip nvcomp-windows-x86_64-4.0.1-cuda12.x.zip
114+
unzip nvcomp-windows-x86_64-4.1.0.6_cuda12-archive.zip
115115
move cudnn-windows-x86_64-9.5.1.17_cuda12-archive\bin\*.dll "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin"
116116
move cudnn-windows-x86_64-9.5.1.17_cuda12-archive\include\*.h "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
117117
move cudnn-windows-x86_64-9.5.1.17_cuda12-archive\lib\x64\*.lib "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\lib\x64"
118118
move dll_x64\zlibwapi.dll "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin"
119-
move nvcomp\include\* "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
120-
move nvcomp\include\device "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
121-
move nvcomp\include\native "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
122-
move nvcomp\include\nvcomp "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
123-
move nvcomp\lib\nvcomp*.dll "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin"
124-
move nvcomp\lib\nvcomp*.lib "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\lib\x64"
119+
move nvcomp-windows-x86_64-4.1.0.6_cuda12-archive\include\* "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
120+
move nvcomp-windows-x86_64-4.1.0.6_cuda12-archive\include\nvcomp "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include"
121+
move nvcomp-windows-x86_64-4.1.0.6_cuda12-archive\bin\nvcomp*.dll "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin"
122+
move nvcomp-windows-x86_64-4.1.0.6_cuda12-archive\bin\nvcomp*.lib "%ProgramFiles%\NVIDIA GPU Computing Toolkit\CUDA\v12.6\lib\x64"
125123
126124
rem echo Applying hotfix to Visual Studio 2019 for CUDA
127125
rem curl -LO https://raw.githubusercontent.com/microsoft/STL/main/stl/inc/cmath
@@ -151,8 +149,8 @@ runs:
151149
152150
if "%CI_DEPLOY_MODULE%"=="mkl" (
153151
echo Installing MKL
154-
curl -LO https://registrationcenter-download.intel.com/akdlm/IRC_NAS/9fe96489-78fe-4fea-8cc2-2ddf7de0246a/w_onemkl_p_2024.2.2.16_offline.exe
155-
w_onemkl_p_2024.2.2.16_offline.exe -s -a -s --eula accept
152+
curl -LO https://registrationcenter-download.intel.com/akdlm/IRC_NAS/e0a45889-f395-47d6-811d-0f3d8caae4a0/intel-onemkl-2025.0.0.929_offline.exe
153+
intel-onemkl-2025.0.0.929_offline.exe -s -a -s --eula accept
156154
)
157155
158156
if "%CI_DEPLOY_PLATFORM%"=="windows-x86" if "%CI_DEPLOY_MODULE%"=="flycapture" (

‎.github/workflows/tritonserver.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,6 +19,6 @@ env:
1919
jobs:
2020
linux-x86_64:
2121
runs-on: ubuntu-20.04
22-
container: nvcr.io/nvidia/tritonserver:24.09-tf2-python-py3
22+
container: nvcr.io/nvidia/tritonserver:24.10-tf2-python-py3
2323
steps:
2424
- uses: bytedeco/javacpp-presets/.github/actions/deploy-ubuntu@actions

‎CHANGELOG.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@
99
* Build FFmpeg with zimg to enable zscale filter ([pull #1481](https://github.com/bytedeco/javacpp-presets/pull/1481))
1010
* Enable PulseAudio support for FFmpeg on Linux ([pull #1472](https://github.com/bytedeco/javacpp-presets/pull/1472))
1111
* Virtualize `btCollisionWorld`, `btOverlapFilterCallback`, `btOverlapCallback` from Bullet Physics SDK ([pull #1475](https://github.com/bytedeco/javacpp-presets/pull/1475))
12-
* Upgrade presets for OpenCV 4.10.0, FFmpeg 7.1, Spinnaker 4.0.0.116 ([pull #1524](https://github.com/bytedeco/javacpp-presets/pull/1524)), MKL 2024.2, DNNL 3.6, OpenBLAS 0.3.28, CMINPACK 1.3.11, GSL 2.8, CPython 3.13.0, NumPy 2.1.2, SciPy 1.14.1, LLVM 19.1.2, LibRaw 0.21.2 ([pull #1520](https://github.com/bytedeco/javacpp-presets/pull/1520)), Leptonica 1.85.0, Tesseract 5.4.1, libffi 3.4.6, CUDA 12.6.2, cuDNN 9.5.1, NCCL 2.23.4, nvCOMP 4.0.1, OpenCL 3.0.16, NVIDIA Video Codec SDK 12.2.72, PyTorch 2.5.0 ([pull #1466](https://github.com/bytedeco/javacpp-presets/pull/1466)), SentencePiece 0.2.0, TensorFlow Lite 2.18.0, TensorRT 10.5.0.18, Triton Inference Server 2.50.0, ONNX 1.17.0, ONNX Runtime 1.19.2, TVM 0.18.0, and their dependencies
12+
* Upgrade presets for OpenCV 4.10.0, FFmpeg 7.1, Spinnaker 4.0.0.116 ([pull #1524](https://github.com/bytedeco/javacpp-presets/pull/1524)), MKL 2025.0, DNNL 3.6, OpenBLAS 0.3.28, CMINPACK 1.3.11, GSL 2.8, CPython 3.13.0, NumPy 2.1.2, SciPy 1.14.1, LLVM 19.1.3, LibRaw 0.21.2 ([pull #1520](https://github.com/bytedeco/javacpp-presets/pull/1520)), Leptonica 1.85.0, Tesseract 5.4.1, libffi 3.4.6, CUDA 12.6.2, cuDNN 9.5.1, NCCL 2.23.4, nvCOMP 4.1.0.6, OpenCL 3.0.16, NVIDIA Video Codec SDK 12.2.72, PyTorch 2.5.1 ([pull #1466](https://github.com/bytedeco/javacpp-presets/pull/1466)), SentencePiece 0.2.0, TensorFlow Lite 2.18.0, TensorRT 10.5.0.18, Triton Inference Server 2.51.0, ONNX 1.17.0, ONNX Runtime 1.19.2, TVM 0.18.0, and their dependencies
1313

1414
### January 29, 2024 version 1.5.10
1515
* Introduce `macosx-arm64` builds for PyTorch ([pull #1463](https://github.com/bytedeco/javacpp-presets/pull/1463))

‎README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -196,7 +196,7 @@ Each child module in turn relies by default on the included [`cppbuild.sh` scrip
196196
* HDF5 1.14.x https://www.hdfgroup.org/downloads/
197197
* Hyperscan 5.4.x https://github.com/intel/hyperscan
198198
* LZ4 1.9.x https://github.com/lz4/lz4
199-
* MKL 2024.x https://software.intel.com/mkl
199+
* MKL 2025.x https://software.intel.com/mkl
200200
* MKL-DNN 0.21.x https://github.com/oneapi-src/oneDNN
201201
* DNNL 3.6.x https://github.com/oneapi-src/oneDNN
202202
* OpenBLAS 0.3.28 http://www.openblas.net/
@@ -219,7 +219,7 @@ Each child module in turn relies by default on the included [`cppbuild.sh` scrip
219219
* CUDA 12.6.x https://developer.nvidia.com/cuda-downloads
220220
* cuDNN 9.5.x https://developer.nvidia.com/cudnn
221221
* NCCL 2.23.x https://developer.nvidia.com/nccl
222-
* nvCOMP 4.0.x https://developer.nvidia.com/nvcomp
222+
* nvCOMP 4.1.x https://developer.nvidia.com/nvcomp
223223
* NVIDIA Video Codec SDK 12.2.x https://developer.nvidia.com/nvidia-video-codec-sdk
224224
* OpenCL 3.0.x https://github.com/KhronosGroup/OpenCL-ICD-Loader
225225
* MXNet 1.9.x https://github.com/apache/incubator-mxnet
@@ -228,7 +228,7 @@ Each child module in turn relies by default on the included [`cppbuild.sh` scrip
228228
* TensorFlow 1.15.x https://github.com/tensorflow/tensorflow
229229
* TensorFlow Lite 2.18.x https://github.com/tensorflow/tensorflow
230230
* TensorRT 10.5.x https://developer.nvidia.com/tensorrt
231-
* Triton Inference Server 2.50.x https://developer.nvidia.com/nvidia-triton-inference-server
231+
* Triton Inference Server 2.51.x https://developer.nvidia.com/nvidia-triton-inference-server
232232
* The Arcade Learning Environment 0.8.x https://github.com/mgbellemare/Arcade-Learning-Environment
233233
* DepthAI 2.24.x https://github.com/luxonis/depthai-core
234234
* ONNX 1.17.x https://github.com/onnx/onnx

‎cuda/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@ This directory contains the JavaCPP Presets module for:
2828
* CUDA 12.6.2 https://developer.nvidia.com/cuda-zone
2929
* cuDNN 9.5.1 https://developer.nvidia.com/cudnn
3030
* NCCL 2.23.4 https://developer.nvidia.com/nccl
31-
* nvCOMP 4.0.1 https://developer.nvidia.com/nvcomp
31+
* nvCOMP 4.1.0.6 https://developer.nvidia.com/nvcomp
3232

3333
Please refer to the parent README.md file for more detailed information about the JavaCPP Presets.
3434

‎cuda/src/gen/java/org/bytedeco/cuda/global/cublas.java

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15038,7 +15038,7 @@ public static native void cublasZtrmm(@Cast("char") byte side,
1503815038
// #include "driver_types.h"
1503915039
// #include "cuComplex.h" /* import complex data type */
1504015040

15041-
// #include "cublas_v2.h"
15041+
// #include "cublas_api.h"
1504215042

1504315043
// #if defined(__cplusplus)
1504415044
// Targeting ../cublas/cublasXtContext.java

‎cuda/src/gen/java/org/bytedeco/cuda/global/cusolver.java

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -370,7 +370,7 @@ public class cusolver extends org.bytedeco.cuda.presets.cusolver {
370370
// #include <stdio.h>
371371

372372
// #include "cuComplex.h" /* import complex data type */
373-
// #include "cublas_v2.h"
373+
// #include "cublas_api.h"
374374
// #include "cusolver_common.h"
375375

376376
/*******************************************************************************/
@@ -14391,7 +14391,7 @@ public class cusolver extends org.bytedeco.cuda.presets.cusolver {
1439114391
// #define CUSOLVERSP_H_
1439214392

1439314393
// #include "cusparse.h"
14394-
// #include "cublas_v2.h"
14394+
// #include "cublas_api.h"
1439514395
// #include "cusolver_common.h"
1439614396

1439714397
// #if defined(__cplusplus)

0 commit comments

Comments
 (0)