Add Python package build infrastructure with modern tooling #44

Copilot · 2026-01-05T08:04:11Z

Python Package Build Support for DEM-Engine (Mesh_Particles Branch)

Completed Implementation

This PR successfully adds the infrastructure to build DEM-Engine as a Python package that can be installed via pip and distributed as a wheel file.

All Tasks Completed

Recent Updates

Version Management:

Changed conda recipe to use hardcoded version number (3.0.0)
Removed git tag-based version detection for simpler manual version control
Version can now be easily updated directly in recipe/meta.yaml

Documented Build Requirements and Fixed Conda Issues:

Added comprehensive documentation for conda users building with pip
Explained need for conda compilers (gxx_linux-64, gcc_linux-64) to prevent library version mismatches
Documented conda-build channel requirements (-c conda-forge flag)
Enhanced troubleshooting section with clear solutions for common build issues
Added comments in conda recipe about channel requirements

Fixed libstdc++ Dependency Issue:

Added libstdcxx-ng >=12 to conda recipe runtime dependencies
This ensures the correct C++ standard library version is available when importing
Fixes GLIBCXX_3.4.30 not found error in conda environments
Added troubleshooting documentation for this issue in PYTHON_BUILD.md

Fixed Multiple Compilation/Binding Issues:

Fixed GetContactForces method signatures* - These methods return size_t and take reference parameters (std::vector<float3>&), not return std::vector<std::vector<std::vector<float>>>. Updated all 6 methods:
- GetContactForcesAndLocalTorque
- GetContactForcesAndLocalTorqueForAll
- GetContactForcesAndGlobalTorque
- GetContactForcesAndGlobalTorqueForAll
- GetContactForces
- GetContactForcesForAll
Added missing GetMass/GetMOI methods - The Python bindings were already expecting these methods but they didn't exist in the C++ classes. Added to:
- DEMClumpTemplate in Structs.h
- DEMExternObj in BdrsAndObjs.h
- DEMMesh in BdrsAndObjs.h
Renamed method in bindings - Changed SetTriWildcardValue to SetPatchWildcardValue to match the current API.

Previous Updates:

Fixed Compilation Error:

Fixed incorrect return type in static_cast for DEMBoxGridSampler and DEMBoxHCPSampler
These functions return std::vector<float3>, not std::vector<std::vector<float>>
The custom float3 type caster converts float3 to Python tuples automatically
DEMCylSurfSampler correctly uses std::vector<std::vector<float>> as that overload exists

Added Missing DEMSolver Methods:

✅ SetMaxTriTriPenetration - Set maximum triangle-triangle penetration margin
✅ SetTriTriPenetration - Manually set triangle-triangle penetration value
✅ SetErrorOutAngularVelocity - Set angular velocity error threshold
✅ DisableJitifyClumpTemplates - Disable jitification of clump templates
✅ DisableJitifyMassProperties - Disable jitification of mass properties
✅ UseCompactForceKernel - Use compact force calculation kernel
✅ SetMeshUniversalContact - Control mesh-mesh contact detection
✅ SetPersistentContact - Enable persistent contact marking
✅ EnableOwnerWildcardOutput - Enable owner wildcard output
✅ EnableContactWildcardOutput - Enable contact wildcard output
✅ EnableGeometryWildcardOutput - Enable geometry wildcard output

All recently added public methods in API.h are now wrapped in the Python bindings.

Conda Installation Support:

✅ Added recipe/meta.yaml for conda-build
✅ Compatible with conda-forge conventions
✅ Supports Linux with CUDA 11.0+
✅ Includes proper C++ standard library dependencies
✅ Updated documentation with conda installation instructions and troubleshooting
✅ Hardcoded version number for easy manual updates

Key Improvements over pyDEME_demo

Modern Standards: Uses pyproject.toml instead of setup.py (PEP 517/518 compliant)
Cleaner Integration: Uses scikit-build-core for seamless CMake integration
Better Organization: Bindings code in separate src/DEM/python/ directory
Less Code Duplication: Refactored CMake linking logic with variables
More Portable: No hardcoded conda paths or environment-specific assumptions
More Robust: Multiple fallbacks for site-packages detection
Better Constants: Uses standard M_PI instead of hardcoded values
Improved Messages: Clear, actionable error and warning messages
Better Documentation: Comprehensive build instructions with troubleshooting
Complete API Coverage: All recent DEMSolver methods are now wrapped
Conda Support: Full conda installation workflow with proper dependencies
Correct Bindings: All method signatures match C++ implementation
Simple Version Management: Hardcoded version for easy updates

Installation

Via pip:

# For conda users, install compilers first:
conda install -c conda-forge gxx_linux-64 gcc_linux-64

# Then install
pip install .

Via conda:

conda install conda-build
conda build recipe/ -c conda-forge
conda install --use-local deme

Create wheel:

pip install build
python -m build

See PYTHON_BUILD.md and IMPLEMENTATION_NOTES.md for detailed information.

Original prompt

Now we need to modify the project's Mesh_Particles branch, so it can be built into a Python package. To do that, we probably need to modify its CMake structure, so we have the option to build a Python package out of it (a whl file and/or something related). DEM-Engine's pyDEME_demo branch already has such an example, and if you compare this branch against the main branch, you can see how the Python wrapping is done. The functionality there is what I want (the Python user should be able to interface the full DEMSolver class and some other auxiliary classes), but the realization there is not that elegant; that's why I would like an overhaul of the Python wrapper. Can you do that?

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

Co-authored-by: Ruochun <[email protected]>

Ruochun · 2026-01-05T12:14:54Z

@copilot I want you to make sure two things: 1. New and recently added DEMSolver methods are wrapped, like SetMaxTriTriPenetration etc. Please do a check. 2. The workflow also allows the package to be conda install-ed. If those already suffice, no change is needed.

Co-authored-by: Ruochun <[email protected]>

Copilot · 2026-01-05T12:22:02Z

@copilot I want you to make sure two things: 1. New and recently added DEMSolver methods are wrapped, like SetMaxTriTriPenetration etc. Please do a check. 2. The workflow also allows the package to be...

Done! I've addressed both requirements:

1. Added missing DEMSolver methods:

SetMaxTriTriPenetration and SetTriTriPenetration ✓
SetErrorOutAngularVelocity ✓
DisableJitifyClumpTemplates and DisableJitifyMassProperties ✓
UseCompactForceKernel, SetMeshUniversalContact, SetPersistentContact ✓
EnableOwnerWildcardOutput, EnableContactWildcardOutput, EnableGeometryWildcardOutput ✓

All 11 missing methods are now wrapped. Commits: 64aef4c and d35b19b

2. Conda installation support:

Added recipe/meta.yaml with proper conda-build configuration ✓
Compatible with conda-forge conventions ✓
Users can now build and install with: conda build recipe/ && conda install --use-local deme ✓

Updated documentation in PYTHON_BUILD.md with both sets of changes.

Co-authored-by: Ruochun <[email protected]>

…ckage

…hub.com/projectchrono/DEM-Engine into copilot/modify-cmake-for-python-package

…ckage

Ruochun · 2026-01-09T17:12:37Z

@copilot When we try to build it, while compiling bindings.cpp, there is the following error pasted at the end. Indeed DDEMBoxGridSampler and other similar methods have alias, and static_casting them here is to clarify the overload, but why do when get this failed casting error? The error: /tmp/build-via-sdist-586gg06z/deme-2.2.0/src/DEM/python/bindings.cpp:128:13: error: invalid ‘static_cast’ from type ‘’ to type ‘std::vector<std::vector > (*)(const std::vector&, const std::vector&, float, float, float)’

The functions return std::vector<float3>, not std::vector<std::vector<float>>. DEMCylSurfSampler correctly uses std::vector<std::vector<float>> as it has that overload. The float3 type caster will automatically convert float3 to Python tuples. Co-authored-by: Ruochun <[email protected]>

Copilot · 2026-01-09T17:16:21Z

@copilot When we try to build it, while compiling bindings.cpp, there is the following error pasted at the end. Indeed DDEMBoxGridSampler and other similar methods have alias, and static_casting them ...

Fixed in commit 1963016.

The issue was that DEMBoxGridSampler and DEMBoxHCPSampler return std::vector<float3>, not std::vector<std::vector<float>>. The static_cast was trying to cast to the wrong return type.

Changed the casts to use the correct return type std::vector<float3>. The custom float3 type caster (defined at the top of bindings.cpp) automatically converts each float3 to a Python tuple, so the result will still be a list of tuples in Python.

DEMCylSurfSampler is correct as-is since it has an overload that actually returns std::vector<std::vector<float>>.

Copilot · 2026-01-15T12:48:38Z

@copilot Now the build works. But after installing the generated whl file, then importing it gives an error: Traceback (most recent call last):
File "/home/ruochunz/DEM-Engine/tt.py", line 1, in <m...

Could you please provide the complete error message? The traceback appears to be cut off. I need to see the full error to diagnose the import issue.

Ruochun · 2026-01-15T13:26:22Z

@copilot The full message is: File "/home/ruochunz/DEM-Engine/tt.py", line 1, in import DEME ImportError: /home/ruochunz/miniconda3/envs/pyDEME_packaging/bin/../lib/libstdc++.so.6: version `GLIBCXX_3.4.30' not found (required by /home/ruochunz/miniconda3/envs/pyDEME_packaging/lib/python3.11/site-packages/DEME.cpython-311-x86_64-linux-gnu.so)

Added libstdcxx-ng >=12 to conda recipe runtime dependencies to ensure the correct C++ standard library version is available when importing the module. This fixes the GLIBCXX_3.4.30 not found error. Also added troubleshooting documentation for this issue. Co-authored-by: Ruochun <[email protected]>

Copilot · 2026-01-15T13:28:45Z

@copilot The full message is: File "/home/ruochunz/DEM-Engine/tt.py", line 1, in import DEME ImportError: /home/ruochunz/miniconda3/envs/pyDEME_packaging/bin/../lib/libstdc++.so.6: version `GLIBCXX_3....

Fixed in commit 36b8dcb.

The error occurs because the module was built with a newer libstdc++ than what's available in the conda environment. Added libstdcxx-ng >=12 to the conda recipe's runtime dependencies to ensure the correct C++ standard library is available.

After rebuilding with conda-build, the package will include this dependency and the import error should be resolved. Also added troubleshooting documentation for this issue in PYTHON_BUILD.md.

Ruochun · 2026-01-15T13:56:03Z

@copilot This error actually happened after installing the generated whl file using pip, instead of having something to do with conda.

Copilot · 2026-01-15T13:58:09Z

@copilot This error actually happened after installing the generated whl file using pip, instead of having something to do with conda.

You're right - this is a pip wheel compatibility issue, not conda-specific. When building with pip install . or python -m build, the wheel links against your system's libstdc++. If that's newer than what's in the conda environment, you get this error.

Solutions:

Build within the conda environment (recommended for conda users):

# Activate your conda env first
conda activate pyDEME_packaging
# Make sure you have the right compilers
conda install -c conda-forge gxx_linux-64 gcc_linux-64
# Then build
pip install .

Use conda-build instead of pip (creates a proper conda package):
```
conda build recipe/
conda install --use-local deme
```
Update libstdc++ in your conda environment:
```
conda install -c conda-forge libstdcxx-ng
```

The conda recipe I added handles this automatically, but pip builds use whatever compiler is active. For conda environments, option 1 or 2 is best.

Ruochun · 2026-01-15T14:46:49Z

@copilot Now the pip whl building and installing route works correctly. Can you write down the pitfall fixing notes (like conda install -c conda-forge gxx_linux-64 gcc_linux-64 to fix gcc problems) somewhere in the documents? Also, the conda installation route is still problematic. When doing conda build recipe/, I got: Attempting to finalize metadata for deme
Channels:

local
Platform: linux-64
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... failed
WARNING: failed to get package records, retrying. exception was: The following packages are not available from current channels:
cmake[version='>=3.18']

Current channels:

file:///home/ruochunz/miniconda3/conda-bld

To search for alternate channels that may provide the conda package you're
looking for, navigate to

https://anaconda.org

and use the search bar at the top of the page.

Channels:

local
Platform: linux-64
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... failed
Channels:
local
Platform: linux-64
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... failed
Channels:
local
Platform: linux-64
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... failed
ERROR: Failed to get package records, max retries exceeded.

PackagesNotFoundError: The following packages are not available from current channels:

cmake[version='>=3.18']

Current channels:

file:///home/ruochunz/miniconda3/conda-bld

To search for alternate channels that may provide the conda package you're
looking for, navigate to

https://anaconda.org

and use the search bar at the top of the page.

1. Added detailed documentation for conda users building with pip: - Need to install gxx_linux-64 and gcc_linux-64 compilers - Prevents GLIBCXX version mismatch errors 2. Fixed conda-build documentation: - Added -c conda-forge flag requirement - Explains this is needed for cmake, ninja, and compiler dependencies 3. Enhanced troubleshooting section: - Compiler issues in conda environments - Conda build packages not found error - Clear solutions for both pip and conda-build workflows Co-authored-by: Ruochun <[email protected]>

Copilot · 2026-01-15T14:52:47Z

@copilot Now the pip whl building and installing route works correctly. Can you write down the pitfall fixing notes (like conda install -c conda-forge gxx_linux-64 gcc_linux-64 to fix gcc problems) so...

Fixed in commit faadcdf.

1. Documented compiler setup pitfalls:
Added detailed instructions in PYTHON_BUILD.md for conda users:

Install gxx_linux-64 and gcc_linux-64 before building with pip
Prevents GLIBCXX version mismatches
Instructions added to Options 1 and 2 (pip and wheel building)

2. Fixed conda-build error:
The issue was missing the -c conda-forge channel flag. Updated documentation to:

conda build recipe/ -c conda-forge

This provides access to cmake, ninja, and other build dependencies. Also added comment in recipe/meta.yaml explaining the channel requirement.

Ruochun · 2026-01-15T15:26:58Z

@copilot The change does help, but I still get the following error pasted at the end of the message. It's also weird that although I changed all version number to 3.0.0, the message still says 2.1.0 at places. It seems that it also failed to find jitify which is in thirdparty folder instead. The error: Adding in variants from internal_defaults
Copying /home/ruochunz/DEM-Engine to /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/
WARNING: No numpy version specified in conda_build_config.yaml. Falling back to default numpy value of 1.23
WARNING: Number of parsed outputs does not match detected raw metadata blocks. Identified output block may be wrong! If you are using Jinja conditionals to include or exclude outputs, consider using skip: true # [condition] instead.
Attempting to finalize metadata for deme
Reloading output folder: ...working... done
Getting pinned dependencies: ...working... done
Reloading output folder: ...working... done
Getting pinned dependencies: ...working... done
Reloading output folder: ...working... done
Getting pinned dependencies: ...working... done
BUILD START: ['deme-2.1.0-py314h3fd9d12_0.conda']
Reloading output folder: ...working... done
Solving environment (_h_env): ...working... done

Package Plan

environment location: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla

The following NEW packages will be INSTALLED:

_libgcc_mutex:       0.1-conda_forge            conda-forge
_openmp_mutex:       4.5-2_gnu                  conda-forge
bzip2:               1.0.8-hda65f42_8           conda-forge
ca-certificates:     2026.1.4-hbd8a1cb_0        conda-forge
cudatoolkit:         11.8.0-h4ba93d1_13         conda-forge
exceptiongroup:      1.3.1-pyhd8ed1ab_0         conda-forge
icu:                 78.2-h33c6efd_0            conda-forge
importlib-metadata:  8.7.0-pyhe01879c_1         conda-forge
importlib-resources: 6.5.2-pyhd8ed1ab_0         conda-forge
importlib_resources: 6.5.2-pyhd8ed1ab_0         conda-forge
ld_impl_linux-64:    2.45-default_hbd61a6d_105  conda-forge
libblas:             3.11.0-5_h4a7cf45_openblas conda-forge
libcblas:            3.11.0-5_h0358290_openblas conda-forge
libexpat:            2.7.3-hecca717_0           conda-forge
libffi:              3.5.2-h9ec8514_0           conda-forge
libgcc:              15.2.0-he0feb66_16         conda-forge
libgcc-ng:           15.2.0-h69a702a_16         conda-forge
libgfortran:         15.2.0-h69a702a_16         conda-forge
libgfortran5:        15.2.0-h68bc16d_16         conda-forge
libgomp:             15.2.0-he0feb66_16         conda-forge
liblapack:           3.11.0-5_h47877c9_openblas conda-forge
liblzma:             5.8.1-hb9d3cd8_2           conda-forge
libmpdec:            4.0.0-hb9d3cd8_0           conda-forge
libopenblas:         0.3.30-pthreads_h94d23a6_4 conda-forge
libsqlite:           3.51.2-hf4e2dac_0          conda-forge
libstdcxx:           15.2.0-h934c35e_16         conda-forge
libstdcxx-ng:        15.2.0-hdf11a46_16         conda-forge
libuuid:             2.41.3-h5347b49_0          conda-forge
libzlib:             1.3.1-hb9d3cd8_2           conda-forge
ncurses:             6.5-h2d0b736_3             conda-forge
numpy:               2.4.1-py314h2b28147_0      conda-forge
openssl:             3.6.0-h26f9b46_0           conda-forge
packaging:           25.0-pyh29332c3_1          conda-forge
pathspec:            1.0.3-pyhd8ed1ab_0         conda-forge
pip:                 25.3-pyh145f28c_0          conda-forge
pybind11:            3.0.1-pyh7a1b43c_0         conda-forge
pybind11-global:     3.0.1-pyhc7ab6ef_0         conda-forge
python:              3.14.2-h32b2ec7_100_cp314  conda-forge
python_abi:          3.14-8_cp314               conda-forge
readline:            8.3-h853b02a_0             conda-forge
scikit-build-core:   0.11.6-pyh7e86bf3_1        conda-forge
tk:                  8.6.13-noxft_ha0e22de_103  conda-forge
tomli:               2.4.0-pyhcf101f3_0         conda-forge
typing-extensions:   4.15.0-h396c80c_0          conda-forge
typing_extensions:   4.15.0-pyhcf101f3_0        conda-forge
tzdata:              2025c-hc9c84f9_1           conda-forge
zipp:                3.23.0-pyhcf101f3_1        conda-forge
zstd:                1.5.7-hb78ec9c_6           conda-forge

Preparing transaction: ...working... done
Verifying transaction: ...working... done
Executing transaction: ...working... By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html

done
Reloading output folder: ...working... done
Solving environment (_build_env): ...working... done
Reloading output folder: ...working... done
Solving environment (_test_env): ...working... done

Package Plan

environment location: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env

The following NEW packages will be INSTALLED:

_libgcc_mutex:            0.1-conda_forge               conda-forge
_openmp_mutex:            4.5-2_gnu                     conda-forge
binutils_impl_linux-64:   2.45-default_hfdba357_105     conda-forge
binutils_linux-64:        2.45-default_h4852527_105     conda-forge
bzip2:                    1.0.8-hda65f42_8              conda-forge
c-ares:                   1.34.6-hb03c661_0             conda-forge
ca-certificates:          2026.1.4-hbd8a1cb_0           conda-forge
cmake:                    4.2.1-hc85cc9f_0              conda-forge
cudatoolkit:              11.8.0-h4ba93d1_13            conda-forge
gcc_impl_linux-64:        15.2.0-hc5723f1_16            conda-forge
gcc_linux-64:             15.2.0-h862fb80_17            conda-forge
gxx_impl_linux-64:        15.2.0-hda75c37_16            conda-forge
gxx_linux-64:             15.2.0-h2d7d49d_17            conda-forge
kernel-headers_linux-64:  5.14.0-he073ed8_3             conda-forge
keyutils:                 1.6.3-hb9d3cd8_0              conda-forge
krb5:                     1.21.3-h659f571_0             conda-forge
ld_impl_linux-64:         2.45-default_hbd61a6d_105     conda-forge
libcurl:                  8.18.0-h4e3cde8_0             conda-forge
libedit:                  3.1.20250104-pl5321h7949ede_0 conda-forge
libev:                    4.33-hd590300_2               conda-forge
libexpat:                 2.7.3-hecca717_0              conda-forge
libgcc:                   15.2.0-he0feb66_16            conda-forge
libgcc-devel_linux-64:    15.2.0-hcc6f6b0_116           conda-forge
libgcc-ng:                15.2.0-h69a702a_16            conda-forge
libgomp:                  15.2.0-he0feb66_16            conda-forge
liblzma:                  5.8.1-hb9d3cd8_2              conda-forge
libnghttp2:               1.67.0-had1ee68_0             conda-forge
libsanitizer:             15.2.0-h90f66d4_16            conda-forge
libssh2:                  1.11.1-hcf80075_0             conda-forge
libstdcxx:                15.2.0-h934c35e_16            conda-forge
libstdcxx-devel_linux-64: 15.2.0-hd446a21_116           conda-forge
libstdcxx-ng:             15.2.0-hdf11a46_16            conda-forge
libuv:                    1.51.0-hb03c661_1             conda-forge
libzlib:                  1.3.1-hb9d3cd8_2              conda-forge
make:                     4.4.1-hb9d3cd8_2              conda-forge
ncurses:                  6.5-h2d0b736_3                conda-forge
ninja:                    1.13.2-h171cf75_0             conda-forge
openssl:                  3.6.0-h26f9b46_0              conda-forge
rhash:                    1.4.6-hb9d3cd8_1              conda-forge
sysroot_linux-64:         2.34-h087de78_3               conda-forge
tzdata:                   2025c-hc9c84f9_1              conda-forge
zstd:                     1.5.7-hb78ec9c_6              conda-forge

Preparing transaction: ...working... done
Verifying transaction: ...working... done
Executing transaction: ...working... By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html

done

Rendered as:

package:
  name: deme
  version: 2.1.0
source:
  path: /home/ruochunz/DEM-Engine
build:
  number: '0'
  script: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python
    -m pip install . -vvv
requirements:
  build:
    - ld_impl_linux-64 2.45 default_hbd61a6d_105
    - cudatoolkit 11.8.0 h4ba93d1_13
    - libgcc-devel_linux-64 15.2.0 hcc6f6b0_116
    - binutils_linux-64 2.45 default_h4852527_105
    - gcc_impl_linux-64 15.2.0 hc5723f1_16
    - libssh2 1.11.1 hcf80075_0
    - rhash 1.4.6 hb9d3cd8_1
    - libgomp 15.2.0 he0feb66_16
    - libstdcxx-ng 15.2.0 hdf11a46_16
    - c-ares 1.34.6 hb03c661_0
    - libstdcxx-devel_linux-64 15.2.0 hd446a21_116
    - bzip2 1.0.8 hda65f42_8
    - ncurses 6.5 h2d0b736_3
    - tzdata 2025c hc9c84f9_1
    - _openmp_mutex 4.5 2_gnu
    - gxx_linux-64 15.2.0 h2d7d49d_17
    - gcc_linux-64 15.2.0 h862fb80_17
    - cmake 4.2.1 hc85cc9f_0
    - libcurl 8.18.0 h4e3cde8_0
    - binutils_impl_linux-64 2.45 default_hfdba357_105
    - libexpat 2.7.3 hecca717_0
    - _libgcc_mutex 0.1 conda_forge
    - libev 4.33 hd590300_2
    - libzlib 1.3.1 hb9d3cd8_2
    - liblzma 5.8.1 hb9d3cd8_2
    - openssl 3.6.0 h26f9b46_0
    - ninja 1.13.2 h171cf75_0
    - ca-certificates 2026.1.4 hbd8a1cb_0
    - sysroot_linux-64 2.34 h087de78_3
    - krb5 1.21.3 h659f571_0
    - libgcc-ng 15.2.0 h69a702a_16
    - libuv 1.51.0 hb03c661_1
    - kernel-headers_linux-64 5.14.0 he073ed8_3
    - make 4.4.1 hb9d3cd8_2
    - libnghttp2 1.67.0 had1ee68_0
    - libstdcxx 15.2.0 h934c35e_16
    - gxx_impl_linux-64 15.2.0 hda75c37_16
    - zstd 1.5.7 hb78ec9c_6
    - libsanitizer 15.2.0 h90f66d4_16
    - keyutils 1.6.3 hb9d3cd8_0
    - libgcc 15.2.0 he0feb66_16
    - libedit 3.1.20250104 pl5321h7949ede_0
  host:
    - _libgcc_mutex 0.1 conda_forge
    - ca-certificates 2026.1.4 hbd8a1cb_0
    - libgomp 15.2.0 he0feb66_16
    - python_abi 3.14 8_cp314
    - tzdata 2025c hc9c84f9_1
    - _openmp_mutex 4.5 2_gnu
    - libgcc 15.2.0 he0feb66_16
    - bzip2 1.0.8 hda65f42_8
    - libexpat 2.7.3 hecca717_0
    - libffi 3.5.2 h9ec8514_0
    - libgcc-ng 15.2.0 h69a702a_16
    - libgfortran5 15.2.0 h68bc16d_16
    - liblzma 5.8.1 hb9d3cd8_2
    - libmpdec 4.0.0 hb9d3cd8_0
    - libstdcxx 15.2.0 h934c35e_16
    - libuuid 2.41.3 h5347b49_0
    - libzlib 1.3.1 hb9d3cd8_2
    - ncurses 6.5 h2d0b736_3
    - openssl 3.6.0 h26f9b46_0
    - icu 78.2 h33c6efd_0
    - libgfortran 15.2.0 h69a702a_16
    - libstdcxx-ng 15.2.0 hdf11a46_16
    - readline 8.3 h853b02a_0
    - tk 8.6.13 noxft_ha0e22de_103
    - zstd 1.5.7 hb78ec9c_6
    - cudatoolkit 11.8.0 h4ba93d1_13
    - ld_impl_linux-64 2.45 default_hbd61a6d_105
    - libopenblas 0.3.30 pthreads_h94d23a6_4
    - libsqlite 3.51.2 hf4e2dac_0
    - libblas 3.11.0 5_h4a7cf45_openblas
    - python 3.14.2 h32b2ec7_100_cp314
    - libcblas 3.11.0 5_h0358290_openblas
    - liblapack 3.11.0 5_h47877c9_openblas
    - packaging 25.0 pyh29332c3_1
    - pathspec 1.0.3 pyhd8ed1ab_0
    - pip 25.3 pyh145f28c_0
    - pybind11-global 3.0.1 pyhc7ab6ef_0
    - tomli 2.4.0 pyhcf101f3_0
    - typing_extensions 4.15.0 pyhcf101f3_0
    - zipp 3.23.0 pyhcf101f3_1
    - exceptiongroup 1.3.1 pyhd8ed1ab_0
    - importlib-metadata 8.7.0 pyhe01879c_1
    - importlib_resources 6.5.2 pyhd8ed1ab_0
    - numpy 2.4.1 py314h2b28147_0
    - pybind11 3.0.1 pyh7a1b43c_0
    - typing-extensions 4.15.0 h396c80c_0
    - importlib-resources 6.5.2 pyhd8ed1ab_0
    - scikit-build-core 0.11.6 pyh7e86bf3_1
  run:
    - numpy >=1.23,<3
    - numpy >=1.19.0
    - python >=3.14,<3.15.0a0
    - python_abi 3.14.* *_cp314
    - libstdcxx >=15
    - cudatoolkit >=11.0
    - libstdcxx-ng >=12
    - libgcc >=15
test:
  imports:
    - DEME
  commands:
    - python -c "import DEME; print('DEME version:', DEME.__file__)"
about:
  home: https://github.com/projectchrono/DEM-Engine
  license: BSD-3-Clause
  license_file: LICENSE.md
  summary: Python bindings for DEM-Engine - a GPU-accelerated Discrete Element Method
    simulation engine
  description: 'DEM-Engine is a GPU-accelerated discrete element method (DEM) simulation
    engine

    that provides high-performance particle and granular dynamics simulations.

    This package provides Python bindings to the DEM-Engine library, allowing

    users to set up and run simulations from Python scripts.

    '
  doc_url: https://github.com/projectchrono/DEM-Engine
  dev_url: https://github.com/projectchrono/DEM-Engine
extra:
  recipe-maintainers:
    - Ruochun
  final: true
  copy_test_source_files: true

source tree in: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
export PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla
export BUILD_PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env
export SRC_DIR=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
INFO: activate-binutils_linux-64.sh made the following environmental changes:
+ADDR2LINE=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-addr2line
+AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ar
+AS=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-as
+CXXFILT=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-c++filt
+ELFEDIT=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-elfedit
+GPROF=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gprof
+LD=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ld
+NM=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-nm
+OBJCOPY=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-objcopy
+OBJDUMP=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-objdump
+RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ranlib
+READELF=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-readelf
+SIZE=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-size
+STRINGS=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-strings
+STRIP=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-strip
INFO: activate-gcc_linux-64.sh made the following environmental changes:
+BUILD=x86_64-conda-linux-gnu
+CC=x86_64-conda-linux-gnu-cc
+CC_FOR_BUILD=x86_64-conda-linux-gnu-cc
+CFLAGS=-march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+CMAKE_ARGS=-DCMAKE_AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ar -DCMAKE_CXX_COMPILER_AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ar -DCMAKE_C_COMPILER_AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ar -DCMAKE_RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ranlib -DCMAKE_CXX_COMPILER_RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ranlib -DCMAKE_C_COMPILER_RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ranlib -DCMAKE_LINKER=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ld -DCMAKE_STRIP=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-strip -DCMAKE_BUILD_TYPE=Release -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=ONLY -DCMAKE_FIND_ROOT_PATH=$PREFIX;$BUILD_PREFIX/x86_64-conda-linux-gnu/sysroot -DCMAKE_INSTALL_PREFIX=$PREFIX -DCMAKE_INSTALL_LIBDIR=lib -DCMAKE_PROGRAM_PATH=$BUILD_PREFIX/bin;$PREFIX/bin
+CMAKE_PREFIX_PATH=$PREFIX:$BUILD_PREFIX/x86_64-conda-linux-gnu/sysroot/usr
+CONDA_BUILD_CROSS_COMPILATION=
+CONDA_BUILD_SYSROOT=$BUILD_PREFIX/x86_64-conda-linux-gnu/sysroot
+CONDA_TOOLCHAIN_BUILD=x86_64-conda-linux-gnu
+CONDA_TOOLCHAIN_HOST=x86_64-conda-linux-gnu
+CPP=x86_64-conda-linux-gnu-cpp
+CPPFLAGS=-DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -isystem $PREFIX/include
+CPP_FOR_BUILD=x86_64-conda-linux-gnu-cpp
+DEBUG_CFLAGS=-march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fvar-tracking-assignments -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+DEBUG_CPPFLAGS=-D_DEBUG -D_FORTIFY_SOURCE=2 -Og -isystem $PREFIX/include
+GCC=x86_64-conda-linux-gnu-gcc
+GCC_AR=x86_64-conda-linux-gnu-gcc-ar
+GCC_NM=x86_64-conda-linux-gnu-gcc-nm
+GCC_RANLIB=x86_64-conda-linux-gnu-gcc-ranlib
+HOST=x86_64-conda-linux-gnu
+LDFLAGS=-Wl,-O2 -Wl,--sort-common -Wl,--as-needed -Wl,-z,relro -Wl,-z,now -Wl,--disable-new-dtags -Wl,--gc-sections -Wl,--allow-shlib-undefined -Wl,-rpath,$PREFIX/lib -Wl,-rpath-link,$PREFIX/lib -L$PREFIX/lib
+LDFLAGS_LD=-O2 --sort-common --as-needed -z relro -z now --disable-new-dtags --gc-sections --allow-shlib-undefined -rpath $PREFIX/lib -rpath-link $PREFIX/lib -L$PREFIX/lib
+MESON_ARGS=-Dbuildtype=release --prefix=$PREFIX -Dlibdir=lib
+build_alias=x86_64-conda-linux-gnu
+host_alias=x86_64-conda-linux-gnu
-BUILD=x86_64-conda_cos6-linux-gnu
INFO: activate-gxx_linux-64.sh made the following environmental changes:
+CXX=x86_64-conda-linux-gnu-c++
+CXXFLAGS=-fvisibility-inlines-hidden -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+CXX_FOR_BUILD=x86_64-conda-linux-gnu-c++
+DEBUG_CXXFLAGS=-fvisibility-inlines-hidden -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fvar-tracking-assignments -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+GXX=x86_64-conda-linux-gnu-g++
Using pip 25.3 from $PREFIX/lib/python3.14/site-packages/pip (python 3.14)
Non-user install because user site-packages disabled
Ignoring indexes: https://pypi.org/simple
Created temporary directory: /tmp/pip-build-tracker-y85sfv50
Initialized build tracking at /tmp/pip-build-tracker-y85sfv50
Created build tracker: /tmp/pip-build-tracker-y85sfv50
Entered build tracker: /tmp/pip-build-tracker-y85sfv50
Created temporary directory: /tmp/pip-install-z03b_lje
Created temporary directory: /tmp/pip-ephem-wheel-cache-kjd8jqf9
Processing $SRC_DIR
Added file://$SRC_DIR to build tracker '/tmp/pip-build-tracker-y85sfv50'
Created temporary directory: /tmp/pip-modern-metadata-rrhm5490
Preparing metadata (pyproject.toml): started
Running command Preparing metadata (pyproject.toml)
*** scikit-build-core 0.11.6 using CMake 4.2.1 (metadata_wheel)
Preparing metadata (pyproject.toml): finished with status 'done'
Source in $SRC_DIR has version 3.0.0, which satisfies requirement deme==3.0.0 from file://$SRC_DIR
Removed deme==3.0.0 from file://$SRC_DIR from build tracker '/tmp/pip-build-tracker-y85sfv50'
Created temporary directory: /tmp/pip-unpack-n0bkq9rp
Building wheels for collected packages: deme
Destination directory: /tmp/pip-ephem-wheel-cache-kjd8jqf9/wheels/0d/92/13/928f4fd292b1bbd81151a60d4d1dddc56bbb732307b7ffa22e/tmp2djxgv9v
Building wheel for deme (pyproject.toml): started
Running command Building wheel for deme (pyproject.toml)
*** scikit-build-core 0.11.6 using CMake 4.2.1 (wheel)
*** Configuring CMake...
2026-01-15 23:12:39,136 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_BUILD_TYPE=Release
2026-01-15 23:12:39,136 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_INSTALL_PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla
2026-01-15 23:12:39,272 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_BUILD_TYPE=Release
2026-01-15 23:12:39,272 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_INSTALL_PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla
loading initial cache file build/cp314-cp314-linux_x86_64/CMakeInit.txt
-- The CXX compiler identification is GNU 15.2.0
-- The CUDA compiler identification is NVIDIA 12.8.93 with host compiler GNU 11.4.0
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Check for working CXX compiler: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env/bin/x86_64-conda-linux-gnu-c++ - skipped
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Detecting CUDA compiler ABI info
-- Detecting CUDA compiler ABI info - done
-- Check for working CUDA compiler: /usr/local/cuda-12.8/bin/nvcc - skipped
-- Detecting CUDA compile features
-- Detecting CUDA compile features - done
-- Found CUDAToolkit: /usr/local/cuda-12.8/targets/x86_64-linux/include (found version "12.8.93")
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
-- Found Threads: TRUE
-- Found Python: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python (found version "3.14.2") found components: Interpreter Development Development.Module Development.Embed
-- pybind11 v3.0.1
-- Performing Test HAS_FLTO_AUTO
-- Performing Test HAS_FLTO_AUTO - Success
-- Python bindings enabled
-- Python version: 3.14.2
-- Python executable: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python
-- Could NOT find libcudacxx (missing: libcudacxx_DIR)
-- Found libcudacxx: /usr/local/cuda-12.8/lib64/cmake/libcudacxx/libcudacxx-config.cmake (found suitable version "2.7.0.0", minimum required is "2.7.0.0")
-- Found CUB: /usr/local/cuda-12.8/lib64/cmake/cub/cub-config.cmake (found version "2.7.0.0")
[C++STD Autodetect] Detecting level of C++ support...
[C++STD Autodetect] Compiler supports C++11...
[C++STD Autodetect] Compiler supports C++14...
[C++STD Autodetect] Compiler supports C++17...
-- ==== Configuring Core Components ====
-- [core] Generating API version header...
-- [core] Extracting NVIDIA Jitify header...
CMake Error: File /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/src/core/NVIDIAJitifyPath-NOTFOUND/jitify.hpp does not exist.
CMake Error at src/core/CMakeLists.txt:18 (configure_file):
configure_file Problem configuring file

-- [core] Generating Runtime Data helper (build)...
-- [core] Generating Runtime Data helper (install)...
-- ==== Building DEM Components ====
-- ==== Building Python Bindings ====
-- ==== Completed Building Python Bindings ====
-- ==== Configuring GPU Algorithm Components ====
-- Demo programs for DEM solver...
-- ...add DEMdemo_Repose
-- ...add DEMdemo_Repose2D
-- ...add DEMdemo_ContactChain
-- ...add DEMdemo_Plow
-- ...add DEMdemo_Sieve
-- ...add DEMdemo_SingleSphereCollide
-- ...add DEMdemo_MeshCollide
-- ...add DEMdemo_MeshFalling
-- ...add DEMdemo_TestPack
-- ...add DEMdemo_RotatingDrum
-- ...add DEMdemo_Centrifuge
-- ...add DEMdemo_GameOfLife
-- ...add DEMdemo_BallDrop
-- ...add DEMdemo_BallDrop2D
-- ...add DEMdemo_Mixer
-- ...add DEMdemo_GRCPrep_Part1
-- ...add DEMdemo_GRCPrep_Part2
-- ...add DEMdemo_GRCPrep_Part3
-- ...add DEMdemo_ConePenetration
-- ...add DEMdemo_Shake
-- ...add DEMdemo_WheelDP
-- ...add DEMdemo_WheelDPSimplified
-- ...add DEMdemo_WheelSlopeSlip
-- ...add DEMdemo_Indentation
-- ...add DEMdemo_SolarSystem
-- ...add DEMdemo_Electrostatic
-- ...add DEMdemo_FlexibleMesh
-- ...add DEMdemo_Hopper_Sphere_Cylinder
-- ...add DEMdemo_Fracture_Box
-- Modular test programs for DEM solver...
-- ...add DEMTest_MeshTemplate
-- ...add DEMTest_PatchLocations
-- ...add DEMTest_MeshPatch
-- Configuring incomplete, errors occurred!

*** CMake configuration failed
error: subprocess-exited-with-error

× Building wheel for deme (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> No available output.

note: This error originates from a subprocess, and is likely not a problem with pip.
full command: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/lib/python3.14/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_wheel /tmp/tmpo4gqnmq2
cwd: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
Building wheel for deme (pyproject.toml): finished with status 'error'
ERROR: Failed building wheel for deme
Failed to build deme
error: failed-wheel-build-for-install

× Failed to build installable wheels for some pyproject.toml based projects
╰─> deme
Exception information:
Traceback (most recent call last):
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/base_command.py", line 107, in _run_wrapper
status = _inner_run()
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/base_command.py", line 98, in _inner_run
return self.run(options, args)
~~~~~~~~^^^^^^^^^^^^^^^
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/req_command.py", line 85, in wrapper
return func(self, options, args)
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/commands/install.py", line 440, in run
raise InstallWheelBuildError(build_failures)
pip._internal.exceptions.InstallWheelBuildError: <InstallWheelBuildError: failed-wheel-build-for-install>
Removed build tracker: '/tmp/pip-build-tracker-y85sfv50'

BuildScriptException: Command '['/bin/bash', '-o', 'errexit', '/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/conda_build.sh']' returned non-zero exit status 1.

Copilot · 2026-01-15T15:28:31Z

@copilot The change does help, but I still get the following error pasted at the end of the message. It's also weird that although I changed all version number to 3.0.0, the message still says 2.1.0 a...

The error message appears to be cut off. Could you please provide the complete error output?

Regarding the issues mentioned:

1. Version showing 2.1.0 instead of 3.0.0:
The version in the recipe comes from environ.get('GIT_DESCRIBE_TAG', '2.1.0'). The '2.1.0' is just a fallback. To use 3.0.0, either:

Tag the git repo: git tag v3.0.0
Or set environment variable: export GIT_DESCRIBE_TAG=v3.0.0 before conda build
Or hardcode it in recipe/meta.yaml: version: 3.0.0

2. jitify not found:
This suggests the MANIFEST.in or source path in the recipe isn't including thirdparty/. Please share the complete error so I can provide the exact fix.

Ruochun · 2026-01-15T15:32:04Z

@copilot Please make it so that I change the version number manually in the yaml file when needed (and this current version is 3.0.0), rather than using git tags. The error is attached, and if it's cut off again, let me know: Adding in variants from internal_defaults
Copying /home/ruochunz/DEM-Engine to /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/
WARNING: No numpy version specified in conda_build_config.yaml. Falling back to default numpy value of 1.23
WARNING: Number of parsed outputs does not match detected raw metadata blocks. Identified output block may be wrong! If you are using Jinja conditionals to include or exclude outputs, consider using skip: true # [condition] instead.
Attempting to finalize metadata for deme
Reloading output folder: ...working... done
Getting pinned dependencies: ...working... done
Reloading output folder: ...working... done
Getting pinned dependencies: ...working... done
Reloading output folder: ...working... done
Getting pinned dependencies: ...working... done
BUILD START: ['deme-2.1.0-py314h3fd9d12_0.conda']
Reloading output folder: ...working... done
Solving environment (_h_env): ...working... done

Package Plan

environment location: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla

The following NEW packages will be INSTALLED:

_libgcc_mutex:       0.1-conda_forge            conda-forge
_openmp_mutex:       4.5-2_gnu                  conda-forge
bzip2:               1.0.8-hda65f42_8           conda-forge
ca-certificates:     2026.1.4-hbd8a1cb_0        conda-forge
cudatoolkit:         11.8.0-h4ba93d1_13         conda-forge
exceptiongroup:      1.3.1-pyhd8ed1ab_0         conda-forge
icu:                 78.2-h33c6efd_0            conda-forge
importlib-metadata:  8.7.0-pyhe01879c_1         conda-forge
importlib-resources: 6.5.2-pyhd8ed1ab_0         conda-forge
importlib_resources: 6.5.2-pyhd8ed1ab_0         conda-forge
ld_impl_linux-64:    2.45-default_hbd61a6d_105  conda-forge
libblas:             3.11.0-5_h4a7cf45_openblas conda-forge
libcblas:            3.11.0-5_h0358290_openblas conda-forge
libexpat:            2.7.3-hecca717_0           conda-forge
libffi:              3.5.2-h9ec8514_0           conda-forge
libgcc:              15.2.0-he0feb66_16         conda-forge
libgcc-ng:           15.2.0-h69a702a_16         conda-forge
libgfortran:         15.2.0-h69a702a_16         conda-forge
libgfortran5:        15.2.0-h68bc16d_16         conda-forge
libgomp:             15.2.0-he0feb66_16         conda-forge
liblapack:           3.11.0-5_h47877c9_openblas conda-forge
liblzma:             5.8.1-hb9d3cd8_2           conda-forge
libmpdec:            4.0.0-hb9d3cd8_0           conda-forge
libopenblas:         0.3.30-pthreads_h94d23a6_4 conda-forge
libsqlite:           3.51.2-hf4e2dac_0          conda-forge
libstdcxx:           15.2.0-h934c35e_16         conda-forge
libstdcxx-ng:        15.2.0-hdf11a46_16         conda-forge
libuuid:             2.41.3-h5347b49_0          conda-forge
libzlib:             1.3.1-hb9d3cd8_2           conda-forge
ncurses:             6.5-h2d0b736_3             conda-forge
numpy:               2.4.1-py314h2b28147_0      conda-forge
openssl:             3.6.0-h26f9b46_0           conda-forge
packaging:           25.0-pyh29332c3_1          conda-forge
pathspec:            1.0.3-pyhd8ed1ab_0         conda-forge
pip:                 25.3-pyh145f28c_0          conda-forge
pybind11:            3.0.1-pyh7a1b43c_0         conda-forge
pybind11-global:     3.0.1-pyhc7ab6ef_0         conda-forge
python:              3.14.2-h32b2ec7_100_cp314  conda-forge
python_abi:          3.14-8_cp314               conda-forge
readline:            8.3-h853b02a_0             conda-forge
scikit-build-core:   0.11.6-pyh7e86bf3_1        conda-forge
tk:                  8.6.13-noxft_ha0e22de_103  conda-forge
tomli:               2.4.0-pyhcf101f3_0         conda-forge
typing-extensions:   4.15.0-h396c80c_0          conda-forge
typing_extensions:   4.15.0-pyhcf101f3_0        conda-forge
tzdata:              2025c-hc9c84f9_1           conda-forge
zipp:                3.23.0-pyhcf101f3_1        conda-forge
zstd:                1.5.7-hb78ec9c_6           conda-forge

Preparing transaction: ...working... done
Verifying transaction: ...working... done
Executing transaction: ...working... By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html

done
Reloading output folder: ...working... done
Solving environment (_build_env): ...working... done
Reloading output folder: ...working... done
Solving environment (_test_env): ...working... done

Package Plan

environment location: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env

The following NEW packages will be INSTALLED:

_libgcc_mutex:            0.1-conda_forge               conda-forge
_openmp_mutex:            4.5-2_gnu                     conda-forge
binutils_impl_linux-64:   2.45-default_hfdba357_105     conda-forge
binutils_linux-64:        2.45-default_h4852527_105     conda-forge
bzip2:                    1.0.8-hda65f42_8              conda-forge
c-ares:                   1.34.6-hb03c661_0             conda-forge
ca-certificates:          2026.1.4-hbd8a1cb_0           conda-forge
cmake:                    4.2.1-hc85cc9f_0              conda-forge
cudatoolkit:              11.8.0-h4ba93d1_13            conda-forge
gcc_impl_linux-64:        15.2.0-hc5723f1_16            conda-forge
gcc_linux-64:             15.2.0-h862fb80_17            conda-forge
gxx_impl_linux-64:        15.2.0-hda75c37_16            conda-forge
gxx_linux-64:             15.2.0-h2d7d49d_17            conda-forge
kernel-headers_linux-64:  5.14.0-he073ed8_3             conda-forge
keyutils:                 1.6.3-hb9d3cd8_0              conda-forge
krb5:                     1.21.3-h659f571_0             conda-forge
ld_impl_linux-64:         2.45-default_hbd61a6d_105     conda-forge
libcurl:                  8.18.0-h4e3cde8_0             conda-forge
libedit:                  3.1.20250104-pl5321h7949ede_0 conda-forge
libev:                    4.33-hd590300_2               conda-forge
libexpat:                 2.7.3-hecca717_0              conda-forge
libgcc:                   15.2.0-he0feb66_16            conda-forge
libgcc-devel_linux-64:    15.2.0-hcc6f6b0_116           conda-forge
libgcc-ng:                15.2.0-h69a702a_16            conda-forge
libgomp:                  15.2.0-he0feb66_16            conda-forge
liblzma:                  5.8.1-hb9d3cd8_2              conda-forge
libnghttp2:               1.67.0-had1ee68_0             conda-forge
libsanitizer:             15.2.0-h90f66d4_16            conda-forge
libssh2:                  1.11.1-hcf80075_0             conda-forge
libstdcxx:                15.2.0-h934c35e_16            conda-forge
libstdcxx-devel_linux-64: 15.2.0-hd446a21_116           conda-forge
libstdcxx-ng:             15.2.0-hdf11a46_16            conda-forge
libuv:                    1.51.0-hb03c661_1             conda-forge
libzlib:                  1.3.1-hb9d3cd8_2              conda-forge
make:                     4.4.1-hb9d3cd8_2              conda-forge
ncurses:                  6.5-h2d0b736_3                conda-forge
ninja:                    1.13.2-h171cf75_0             conda-forge
openssl:                  3.6.0-h26f9b46_0              conda-forge
rhash:                    1.4.6-hb9d3cd8_1              conda-forge
sysroot_linux-64:         2.34-h087de78_3               conda-forge
tzdata:                   2025c-hc9c84f9_1              conda-forge
zstd:                     1.5.7-hb78ec9c_6              conda-forge

Preparing transaction: ...working... done
Verifying transaction: ...working... done
Executing transaction: ...working... By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html

done

Rendered as:

package:
  name: deme
  version: 2.1.0
source:
  path: /home/ruochunz/DEM-Engine
build:
  number: '0'
  script: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python
    -m pip install . -vvv
requirements:
  build:
    - ld_impl_linux-64 2.45 default_hbd61a6d_105
    - cudatoolkit 11.8.0 h4ba93d1_13
    - libgcc-devel_linux-64 15.2.0 hcc6f6b0_116
    - binutils_linux-64 2.45 default_h4852527_105
    - gcc_impl_linux-64 15.2.0 hc5723f1_16
    - libssh2 1.11.1 hcf80075_0
    - rhash 1.4.6 hb9d3cd8_1
    - libgomp 15.2.0 he0feb66_16
    - libstdcxx-ng 15.2.0 hdf11a46_16
    - c-ares 1.34.6 hb03c661_0
    - libstdcxx-devel_linux-64 15.2.0 hd446a21_116
    - bzip2 1.0.8 hda65f42_8
    - ncurses 6.5 h2d0b736_3
    - tzdata 2025c hc9c84f9_1
    - _openmp_mutex 4.5 2_gnu
    - gxx_linux-64 15.2.0 h2d7d49d_17
    - gcc_linux-64 15.2.0 h862fb80_17
    - cmake 4.2.1 hc85cc9f_0
    - libcurl 8.18.0 h4e3cde8_0
    - binutils_impl_linux-64 2.45 default_hfdba357_105
    - libexpat 2.7.3 hecca717_0
    - _libgcc_mutex 0.1 conda_forge
    - libev 4.33 hd590300_2
    - libzlib 1.3.1 hb9d3cd8_2
    - liblzma 5.8.1 hb9d3cd8_2
    - openssl 3.6.0 h26f9b46_0
    - ninja 1.13.2 h171cf75_0
    - ca-certificates 2026.1.4 hbd8a1cb_0
    - sysroot_linux-64 2.34 h087de78_3
    - krb5 1.21.3 h659f571_0
    - libgcc-ng 15.2.0 h69a702a_16
    - libuv 1.51.0 hb03c661_1
    - kernel-headers_linux-64 5.14.0 he073ed8_3
    - make 4.4.1 hb9d3cd8_2
    - libnghttp2 1.67.0 had1ee68_0
    - libstdcxx 15.2.0 h934c35e_16
    - gxx_impl_linux-64 15.2.0 hda75c37_16
    - zstd 1.5.7 hb78ec9c_6
    - libsanitizer 15.2.0 h90f66d4_16
    - keyutils 1.6.3 hb9d3cd8_0
    - libgcc 15.2.0 he0feb66_16
    - libedit 3.1.20250104 pl5321h7949ede_0
  host:
    - _libgcc_mutex 0.1 conda_forge
    - ca-certificates 2026.1.4 hbd8a1cb_0
    - libgomp 15.2.0 he0feb66_16
    - python_abi 3.14 8_cp314
    - tzdata 2025c hc9c84f9_1
    - _openmp_mutex 4.5 2_gnu
    - libgcc 15.2.0 he0feb66_16
    - bzip2 1.0.8 hda65f42_8
    - libexpat 2.7.3 hecca717_0
    - libffi 3.5.2 h9ec8514_0
    - libgcc-ng 15.2.0 h69a702a_16
    - libgfortran5 15.2.0 h68bc16d_16
    - liblzma 5.8.1 hb9d3cd8_2
    - libmpdec 4.0.0 hb9d3cd8_0
    - libstdcxx 15.2.0 h934c35e_16
    - libuuid 2.41.3 h5347b49_0
    - libzlib 1.3.1 hb9d3cd8_2
    - ncurses 6.5 h2d0b736_3
    - openssl 3.6.0 h26f9b46_0
    - icu 78.2 h33c6efd_0
    - libgfortran 15.2.0 h69a702a_16
    - libstdcxx-ng 15.2.0 hdf11a46_16
    - readline 8.3 h853b02a_0
    - tk 8.6.13 noxft_ha0e22de_103
    - zstd 1.5.7 hb78ec9c_6
    - cudatoolkit 11.8.0 h4ba93d1_13
    - ld_impl_linux-64 2.45 default_hbd61a6d_105
    - libopenblas 0.3.30 pthreads_h94d23a6_4
    - libsqlite 3.51.2 hf4e2dac_0
    - libblas 3.11.0 5_h4a7cf45_openblas
    - python 3.14.2 h32b2ec7_100_cp314
    - libcblas 3.11.0 5_h0358290_openblas
    - liblapack 3.11.0 5_h47877c9_openblas
    - packaging 25.0 pyh29332c3_1
    - pathspec 1.0.3 pyhd8ed1ab_0
    - pip 25.3 pyh145f28c_0
    - pybind11-global 3.0.1 pyhc7ab6ef_0
    - tomli 2.4.0 pyhcf101f3_0
    - typing_extensions 4.15.0 pyhcf101f3_0
    - zipp 3.23.0 pyhcf101f3_1
    - exceptiongroup 1.3.1 pyhd8ed1ab_0
    - importlib-metadata 8.7.0 pyhe01879c_1
    - importlib_resources 6.5.2 pyhd8ed1ab_0
    - numpy 2.4.1 py314h2b28147_0
    - pybind11 3.0.1 pyh7a1b43c_0
    - typing-extensions 4.15.0 h396c80c_0
    - importlib-resources 6.5.2 pyhd8ed1ab_0
    - scikit-build-core 0.11.6 pyh7e86bf3_1
  run:
    - numpy >=1.23,<3
    - numpy >=1.19.0
    - python >=3.14,<3.15.0a0
    - python_abi 3.14.* *_cp314
    - libstdcxx >=15
    - cudatoolkit >=11.0
    - libstdcxx-ng >=12
    - libgcc >=15
test:
  imports:
    - DEME
  commands:
    - python -c "import DEME; print('DEME version:', DEME.__file__)"
about:
  home: https://github.com/projectchrono/DEM-Engine
  license: BSD-3-Clause
  license_file: LICENSE.md
  summary: Python bindings for DEM-Engine - a GPU-accelerated Discrete Element Method
    simulation engine
  description: 'DEM-Engine is a GPU-accelerated discrete element method (DEM) simulation
    engine

    that provides high-performance particle and granular dynamics simulations.

    This package provides Python bindings to the DEM-Engine library, allowing

    users to set up and run simulations from Python scripts.

    '
  doc_url: https://github.com/projectchrono/DEM-Engine
  dev_url: https://github.com/projectchrono/DEM-Engine
extra:
  recipe-maintainers:
    - Ruochun
  final: true
  copy_test_source_files: true

source tree in: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
export PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla
export BUILD_PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env
export SRC_DIR=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
INFO: activate-binutils_linux-64.sh made the following environmental changes:
+ADDR2LINE=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-addr2line
+AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ar
+AS=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-as
+CXXFILT=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-c++filt
+ELFEDIT=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-elfedit
+GPROF=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gprof
+LD=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ld
+NM=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-nm
+OBJCOPY=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-objcopy
+OBJDUMP=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-objdump
+RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ranlib
+READELF=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-readelf
+SIZE=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-size
+STRINGS=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-strings
+STRIP=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-strip
INFO: activate-gcc_linux-64.sh made the following environmental changes:
+BUILD=x86_64-conda-linux-gnu
+CC=x86_64-conda-linux-gnu-cc
+CC_FOR_BUILD=x86_64-conda-linux-gnu-cc
+CFLAGS=-march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+CMAKE_ARGS=-DCMAKE_AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ar -DCMAKE_CXX_COMPILER_AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ar -DCMAKE_C_COMPILER_AR=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ar -DCMAKE_RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ranlib -DCMAKE_CXX_COMPILER_RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ranlib -DCMAKE_C_COMPILER_RANLIB=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-gcc-ranlib -DCMAKE_LINKER=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-ld -DCMAKE_STRIP=$BUILD_PREFIX/bin/x86_64-conda-linux-gnu-strip -DCMAKE_BUILD_TYPE=Release -DCMAKE_FIND_ROOT_PATH_MODE_PROGRAM=NEVER -DCMAKE_FIND_ROOT_PATH_MODE_LIBRARY=ONLY -DCMAKE_FIND_ROOT_PATH_MODE_INCLUDE=ONLY -DCMAKE_FIND_ROOT_PATH=$PREFIX;$BUILD_PREFIX/x86_64-conda-linux-gnu/sysroot -DCMAKE_INSTALL_PREFIX=$PREFIX -DCMAKE_INSTALL_LIBDIR=lib -DCMAKE_PROGRAM_PATH=$BUILD_PREFIX/bin;$PREFIX/bin
+CMAKE_PREFIX_PATH=$PREFIX:$BUILD_PREFIX/x86_64-conda-linux-gnu/sysroot/usr
+CONDA_BUILD_CROSS_COMPILATION=
+CONDA_BUILD_SYSROOT=$BUILD_PREFIX/x86_64-conda-linux-gnu/sysroot
+CONDA_TOOLCHAIN_BUILD=x86_64-conda-linux-gnu
+CONDA_TOOLCHAIN_HOST=x86_64-conda-linux-gnu
+CPP=x86_64-conda-linux-gnu-cpp
+CPPFLAGS=-DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -isystem $PREFIX/include
+CPP_FOR_BUILD=x86_64-conda-linux-gnu-cpp
+DEBUG_CFLAGS=-march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fvar-tracking-assignments -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+DEBUG_CPPFLAGS=-D_DEBUG -D_FORTIFY_SOURCE=2 -Og -isystem $PREFIX/include
+GCC=x86_64-conda-linux-gnu-gcc
+GCC_AR=x86_64-conda-linux-gnu-gcc-ar
+GCC_NM=x86_64-conda-linux-gnu-gcc-nm
+GCC_RANLIB=x86_64-conda-linux-gnu-gcc-ranlib
+HOST=x86_64-conda-linux-gnu
+LDFLAGS=-Wl,-O2 -Wl,--sort-common -Wl,--as-needed -Wl,-z,relro -Wl,-z,now -Wl,--disable-new-dtags -Wl,--gc-sections -Wl,--allow-shlib-undefined -Wl,-rpath,$PREFIX/lib -Wl,-rpath-link,$PREFIX/lib -L$PREFIX/lib
+LDFLAGS_LD=-O2 --sort-common --as-needed -z relro -z now --disable-new-dtags --gc-sections --allow-shlib-undefined -rpath $PREFIX/lib -rpath-link $PREFIX/lib -L$PREFIX/lib
+MESON_ARGS=-Dbuildtype=release --prefix=$PREFIX -Dlibdir=lib
+build_alias=x86_64-conda-linux-gnu
+host_alias=x86_64-conda-linux-gnu
-BUILD=x86_64-conda_cos6-linux-gnu
INFO: activate-gxx_linux-64.sh made the following environmental changes:
+CXX=x86_64-conda-linux-gnu-c++
+CXXFLAGS=-fvisibility-inlines-hidden -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+CXX_FOR_BUILD=x86_64-conda-linux-gnu-c++
+DEBUG_CXXFLAGS=-fvisibility-inlines-hidden -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-all -fno-plt -Og -g -Wall -Wextra -fvar-tracking-assignments -ffunction-sections -pipe -isystem $PREFIX/include -fdebug-prefix-map=$SRC_DIR=/usr/local/src/conda/deme-2.1.0 -fdebug-prefix-map=$PREFIX=/usr/local/src/conda-prefix
+GXX=x86_64-conda-linux-gnu-g++
Using pip 25.3 from $PREFIX/lib/python3.14/site-packages/pip (python 3.14)
Non-user install because user site-packages disabled
Ignoring indexes: https://pypi.org/simple
Created temporary directory: /tmp/pip-build-tracker-y85sfv50
Initialized build tracking at /tmp/pip-build-tracker-y85sfv50
Created build tracker: /tmp/pip-build-tracker-y85sfv50
Entered build tracker: /tmp/pip-build-tracker-y85sfv50
Created temporary directory: /tmp/pip-install-z03b_lje
Created temporary directory: /tmp/pip-ephem-wheel-cache-kjd8jqf9
Processing $SRC_DIR
Added file://$SRC_DIR to build tracker '/tmp/pip-build-tracker-y85sfv50'
Created temporary directory: /tmp/pip-modern-metadata-rrhm5490
Preparing metadata (pyproject.toml): started
Running command Preparing metadata (pyproject.toml)
*** scikit-build-core 0.11.6 using CMake 4.2.1 (metadata_wheel)
Preparing metadata (pyproject.toml): finished with status 'done'
Source in $SRC_DIR has version 3.0.0, which satisfies requirement deme==3.0.0 from file://$SRC_DIR
Removed deme==3.0.0 from file://$SRC_DIR from build tracker '/tmp/pip-build-tracker-y85sfv50'
Created temporary directory: /tmp/pip-unpack-n0bkq9rp
Building wheels for collected packages: deme
Destination directory: /tmp/pip-ephem-wheel-cache-kjd8jqf9/wheels/0d/92/13/928f4fd292b1bbd81151a60d4d1dddc56bbb732307b7ffa22e/tmp2djxgv9v
Building wheel for deme (pyproject.toml): started
Running command Building wheel for deme (pyproject.toml)
*** scikit-build-core 0.11.6 using CMake 4.2.1 (wheel)
*** Configuring CMake...
2026-01-15 23:12:39,136 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_BUILD_TYPE=Release
2026-01-15 23:12:39,136 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_INSTALL_PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla
2026-01-15 23:12:39,272 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_BUILD_TYPE=Release
2026-01-15 23:12:39,272 - scikit_build_core - WARNING - Unsupported CMAKE_ARGS ignored: -DCMAKE_INSTALL_PREFIX=/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla
loading initial cache file build/cp314-cp314-linux_x86_64/CMakeInit.txt
-- The CXX compiler identification is GNU 15.2.0
-- The CUDA compiler identification is NVIDIA 12.8.93 with host compiler GNU 11.4.0
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Check for working CXX compiler: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env/bin/x86_64-conda-linux-gnu-c++ - skipped
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Detecting CUDA compiler ABI info
-- Detecting CUDA compiler ABI info - done
-- Check for working CUDA compiler: /usr/local/cuda-12.8/bin/nvcc - skipped
-- Detecting CUDA compile features
-- Detecting CUDA compile features - done
-- Found CUDAToolkit: /usr/local/cuda-12.8/targets/x86_64-linux/include (found version "12.8.93")
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
-- Found Threads: TRUE
-- Found Python: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python (found version "3.14.2") found components: Interpreter Development Development.Module Development.Embed
-- pybind11 v3.0.1
-- Performing Test HAS_FLTO_AUTO
-- Performing Test HAS_FLTO_AUTO - Success
-- Python bindings enabled
-- Python version: 3.14.2
-- Python executable: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python
-- Could NOT find libcudacxx (missing: libcudacxx_DIR)
-- Found libcudacxx: /usr/local/cuda-12.8/lib64/cmake/libcudacxx/libcudacxx-config.cmake (found suitable version "2.7.0.0", minimum required is "2.7.0.0")
-- Found CUB: /usr/local/cuda-12.8/lib64/cmake/cub/cub-config.cmake (found version "2.7.0.0")
[C++STD Autodetect] Detecting level of C++ support...
[C++STD Autodetect] Compiler supports C++11...
[C++STD Autodetect] Compiler supports C++14...
[C++STD Autodetect] Compiler supports C++17...
-- ==== Configuring Core Components ====
-- [core] Generating API version header...
-- [core] Extracting NVIDIA Jitify header...
CMake Error: File /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/src/core/NVIDIAJitifyPath-NOTFOUND/jitify.hpp does not exist.
CMake Error at src/core/CMakeLists.txt:18 (configure_file):
configure_file Problem configuring file

-- [core] Generating Runtime Data helper (build)...
-- [core] Generating Runtime Data helper (install)...
-- ==== Building DEM Components ====
-- ==== Building Python Bindings ====
-- ==== Completed Building Python Bindings ====
-- ==== Configuring GPU Algorithm Components ====
-- Demo programs for DEM solver...
-- ...add DEMdemo_Repose
-- ...add DEMdemo_Repose2D
-- ...add DEMdemo_ContactChain
-- ...add DEMdemo_Plow
-- ...add DEMdemo_Sieve
-- ...add DEMdemo_SingleSphereCollide
-- ...add DEMdemo_MeshCollide
-- ...add DEMdemo_MeshFalling
-- ...add DEMdemo_TestPack
-- ...add DEMdemo_RotatingDrum
-- ...add DEMdemo_Centrifuge
-- ...add DEMdemo_GameOfLife
-- ...add DEMdemo_BallDrop
-- ...add DEMdemo_BallDrop2D
-- ...add DEMdemo_Mixer
-- ...add DEMdemo_GRCPrep_Part1
-- ...add DEMdemo_GRCPrep_Part2
-- ...add DEMdemo_GRCPrep_Part3
-- ...add DEMdemo_ConePenetration
-- ...add DEMdemo_Shake
-- ...add DEMdemo_WheelDP
-- ...add DEMdemo_WheelDPSimplified
-- ...add DEMdemo_WheelSlopeSlip
-- ...add DEMdemo_Indentation
-- ...add DEMdemo_SolarSystem
-- ...add DEMdemo_Electrostatic
-- ...add DEMdemo_FlexibleMesh
-- ...add DEMdemo_Hopper_Sphere_Cylinder
-- ...add DEMdemo_Fracture_Box
-- Modular test programs for DEM solver...
-- ...add DEMTest_MeshTemplate
-- ...add DEMTest_PatchLocations
-- ...add DEMTest_MeshPatch
-- Configuring incomplete, errors occurred!

*** CMake configuration failed
error: subprocess-exited-with-error

× Building wheel for deme (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> No available output.

note: This error originates from a subprocess, and is likely not a problem with pip.
full command: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/lib/python3.14/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_wheel /tmp/tmpo4gqnmq2
cwd: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
Building wheel for deme (pyproject.toml): finished with status 'error'
ERROR: Failed building wheel for deme
Failed to build deme
error: failed-wheel-build-for-install

× Failed to build installable wheels for some pyproject.toml based projects
╰─> deme
Exception information:
Traceback (most recent call last):
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/base_command.py", line 107, in _run_wrapper
status = _inner_run()
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/base_command.py", line 98, in _inner_run
return self.run(options, args)
~~~~~~~~^^^^^^^^^^^^^^^
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/req_command.py", line 85, in wrapper
return func(self, options, args)
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/commands/install.py", line 440, in run
raise InstallWheelBuildError(build_failures)
pip._internal.exceptions.InstallWheelBuildError: <InstallWheelBuildError: failed-wheel-build-for-install>
Removed build tracker: '/tmp/pip-build-tracker-y85sfv50'

BuildScriptException: Command '['/bin/bash', '-o', 'errexit', '/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/conda_build.sh']' returned non-zero exit status 1.

Removed git tag-based version detection. Version is now manually set to 3.0.0 in recipe/meta.yaml and can be easily updated as needed. Co-authored-by: Ruochun <[email protected]>

Copilot · 2026-01-15T15:35:29Z

@copilot Please make it so that I change the version number manually in the yaml file when needed (and this current version is 3.0.0), rather than using git tags. The error is attached, and if it's cu...

Fixed the version issue in commit 6ef9f59. The version is now hardcoded to 3.0.0 in recipe/meta.yaml and can be manually updated whenever needed.

However, the error message is still cut off. The output shows package installation starting but doesn't show the actual error. Could you please provide the complete error output, particularly the part after "The following NEW packages will be INSTALLED" where it shows the actual build failure?

I need to see the CMake or compilation error to fix the jitify issue you mentioned.

Ruochun · 2026-01-15T15:44:08Z

@copilot Let me know if this works (last parts of the build output): loading initial cache file build/cp314-cp314-linux_x86_64/CMakeInit.txt
-- The CXX compiler identification is GNU 15.2.0
-- The CUDA compiler identification is NVIDIA 12.8.93 with host compiler GNU 11.4.0
-- Detecting CXX compiler ABI info
-- Detecting CXX compiler ABI info - done
-- Check for working CXX compiler: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_build_env/bin/x86_64-conda-linux-gnu-c++ - skipped
-- Detecting CXX compile features
-- Detecting CXX compile features - done
-- Detecting CUDA compiler ABI info
-- Detecting CUDA compiler ABI info - done
-- Check for working CUDA compiler: /usr/local/cuda-12.8/bin/nvcc - skipped
-- Detecting CUDA compile features
-- Detecting CUDA compile features - done
-- Found CUDAToolkit: /usr/local/cuda-12.8/targets/x86_64-linux/include (found version "12.8.93")
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD
-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
-- Found Threads: TRUE
-- Found Python: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python (found version "3.14.2") found components: Interpreter Development Development.Module Development.Embed
-- pybind11 v3.0.1
-- Performing Test HAS_FLTO_AUTO
-- Performing Test HAS_FLTO_AUTO - Success
-- Python bindings enabled
-- Python version: 3.14.2
-- Python executable: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python
-- Could NOT find libcudacxx (missing: libcudacxx_DIR)
-- Found libcudacxx: /usr/local/cuda-12.8/lib64/cmake/libcudacxx/libcudacxx-config.cmake (found suitable version "2.7.0.0", minimum required is "2.7.0.0")
-- Found CUB: /usr/local/cuda-12.8/lib64/cmake/cub/cub-config.cmake (found version "2.7.0.0")
[C++STD Autodetect] Detecting level of C++ support...
[C++STD Autodetect] Compiler supports C++11...
[C++STD Autodetect] Compiler supports C++14...
[C++STD Autodetect] Compiler supports C++17...
-- ==== Configuring Core Components ====
-- [core] Generating API version header...
-- [core] Extracting NVIDIA Jitify header...
CMake Error: File /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/src/core/NVIDIAJitifyPath-NOTFOUND/jitify.hpp does not exist.
CMake Error at src/core/CMakeLists.txt:18 (configure_file):
configure_file Problem configuring file

-- [core] Generating Runtime Data helper (build)...
-- [core] Generating Runtime Data helper (install)...
-- ==== Building DEM Components ====
-- ==== Building Python Bindings ====
-- ==== Completed Building Python Bindings ====
-- ==== Configuring GPU Algorithm Components ====
-- Demo programs for DEM solver...
-- ...add DEMdemo_Repose
-- ...add DEMdemo_Repose2D
-- ...add DEMdemo_ContactChain
-- ...add DEMdemo_Plow
-- ...add DEMdemo_Sieve
-- ...add DEMdemo_SingleSphereCollide
-- ...add DEMdemo_MeshCollide
-- ...add DEMdemo_MeshFalling
-- ...add DEMdemo_TestPack
-- ...add DEMdemo_RotatingDrum
-- ...add DEMdemo_Centrifuge
-- ...add DEMdemo_GameOfLife
-- ...add DEMdemo_BallDrop
-- ...add DEMdemo_BallDrop2D
-- ...add DEMdemo_Mixer
-- ...add DEMdemo_GRCPrep_Part1
-- ...add DEMdemo_GRCPrep_Part2
-- ...add DEMdemo_GRCPrep_Part3
-- ...add DEMdemo_ConePenetration
-- ...add DEMdemo_Shake
-- ...add DEMdemo_WheelDP
-- ...add DEMdemo_WheelDPSimplified
-- ...add DEMdemo_WheelSlopeSlip
-- ...add DEMdemo_Indentation
-- ...add DEMdemo_SolarSystem
-- ...add DEMdemo_Electrostatic
-- ...add DEMdemo_FlexibleMesh
-- ...add DEMdemo_Hopper_Sphere_Cylinder
-- ...add DEMdemo_Fracture_Box
-- Modular test programs for DEM solver...
-- ...add DEMTest_MeshTemplate
-- ...add DEMTest_PatchLocations
-- ...add DEMTest_MeshPatch
-- Configuring incomplete, errors occurred!

*** CMake configuration failed
error: subprocess-exited-with-error

× Building wheel for deme (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> No available output.

note: This error originates from a subprocess, and is likely not a problem with pip.
full command: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/bin/python /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pla/lib/python3.14/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_wheel /tmp/tmpo4gqnmq2
cwd: /home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work
Building wheel for deme (pyproject.toml): finished with status 'error'
ERROR: Failed building wheel for deme
Failed to build deme
error: failed-wheel-build-for-install

× Failed to build installable wheels for some pyproject.toml based projects
╰─> deme
Exception information:
Traceback (most recent call last):
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/base_command.py", line 107, in _run_wrapper
status = _inner_run()
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/base_command.py", line 98, in _inner_run
return self.run(options, args)
~~~~~~~~^^^^^^^^^^^^^^^
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/cli/req_command.py", line 85, in wrapper
return func(self, options, args)
File "$PREFIX/lib/python3.14/site-packages/pip/_internal/commands/install.py", line 440, in run
raise InstallWheelBuildError(build_failures)
pip._internal.exceptions.InstallWheelBuildError: <InstallWheelBuildError: failed-wheel-build-for-install>
Removed build tracker: '/tmp/pip-build-tracker-y85sfv50'

BuildScriptException: Command '['/bin/bash', '-o', 'errexit', '/home/ruochunz/miniconda3/conda-bld/deme_1768489850829/work/conda_build.sh']' returned non-zero exit status 1.

Initial plan

251bf43

Copilot AI assigned Copilot and Ruochun Jan 5, 2026

Copilot started work on behalf of Ruochun January 5, 2026 08:04 View session

Copilot AI and others added 6 commits January 5, 2026 08:11

Add Python package build infrastructure

3eaab37

Co-authored-by: Ruochun <[email protected]>

Fix float4 type caster size check bug

d16db4b

Co-authored-by: Ruochun <[email protected]>

Clean up bindings: remove duplicate include and fix typo

36944f0

Co-authored-by: Ruochun <[email protected]>

Improve robustness and reduce code duplication

d557b2e

Co-authored-by: Ruochun <[email protected]>

Address code review feedback: improve messages and documentation

cca3939

Co-authored-by: Ruochun <[email protected]>

Add implementation notes and complete Python package support

b34ad2b

Co-authored-by: Ruochun <[email protected]>

Copilot AI changed the title ~~[WIP] Update CMake structure to support Python package build~~ Add Python package build infrastructure with modern tooling Jan 5, 2026

Copilot AI requested a review from Ruochun January 5, 2026 08:21

Copilot finished work on behalf of Ruochun January 5, 2026 08:21

Copilot started work on behalf of Ruochun January 5, 2026 12:15 View session

Copilot AI and others added 2 commits January 5, 2026 12:21

Add missing DEMSolver methods to Python bindings and conda recipe

64aef4c

Co-authored-by: Ruochun <[email protected]>

Update documentation with new methods and conda installation

d35b19b

Co-authored-by: Ruochun <[email protected]>

Fix typo: thinckness -> thickness

7c8ff07

Co-authored-by: Ruochun <[email protected]>

Copilot finished work on behalf of Ruochun January 5, 2026 12:24

Ruochun added 5 commits January 7, 2026 00:24

Merge branch 'Mesh_Particles' into copilot/modify-cmake-for-python-pa…

fa7eb4c

…ckage

Merge branch 'copilot/modify-cmake-for-python-package' of https://git…

aa6079f

…hub.com/projectchrono/DEM-Engine into copilot/modify-cmake-for-python-package

Fix some inclusion errors

b6eba7e

Merge branch 'Mesh_Particles' into copilot/modify-cmake-for-python-pa…

c38ed5c

…ckage

Organize DEME paths

f6bf5bc

Copilot started work on behalf of Ruochun January 9, 2026 17:13 View session

Copilot finished work on behalf of Ruochun January 9, 2026 17:17

Copilot finished work on behalf of Ruochun January 15, 2026 12:49

Copilot started work on behalf of Ruochun January 15, 2026 13:26 View session

Copilot finished work on behalf of Ruochun January 15, 2026 13:29

Copilot started work on behalf of Ruochun January 15, 2026 13:56 View session

Copilot finished work on behalf of Ruochun January 15, 2026 13:59

Make pip whl work correctly

f4c3dca

Copilot started work on behalf of Ruochun January 15, 2026 14:47 View session

Copilot finished work on behalf of Ruochun January 15, 2026 14:57

yaml changes to 3.0.0

9f6b044

Copilot started work on behalf of Ruochun January 15, 2026 15:27 View session

Copilot finished work on behalf of Ruochun January 15, 2026 15:29

Copilot started work on behalf of Ruochun January 15, 2026 15:32 View session

Change version to hardcoded 3.0.0 in conda recipe

6ef9f59

Removed git tag-based version detection. Version is now manually set to 3.0.0 in recipe/meta.yaml and can be easily updated as needed. Co-authored-by: Ruochun <[email protected]>

Copilot finished work on behalf of Ruochun January 15, 2026 15:36

Copilot started work on behalf of Ruochun January 15, 2026 15:46 View session

Copilot finished work on behalf of Ruochun January 16, 2026 04:12

Add Python package build infrastructure with modern tooling #44

Are you sure you want to change the base?

Add Python package build infrastructure with modern tooling #44

Uh oh!

Conversation

Copilot AI commented Jan 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Python Package Build Support for DEM-Engine (Mesh_Particles Branch)

Completed Implementation

All Tasks Completed

Recent Updates

Key Improvements over pyDEME_demo

Installation

Uh oh!

Ruochun commented Jan 5, 2026

Uh oh!

Copilot AI commented Jan 5, 2026

Uh oh!

Ruochun commented Jan 9, 2026

Uh oh!

Copilot AI commented Jan 9, 2026

Uh oh!

Copilot AI commented Jan 15, 2026

Uh oh!

Ruochun commented Jan 15, 2026

Uh oh!

Copilot AI commented Jan 15, 2026

Uh oh!

Ruochun commented Jan 15, 2026

Uh oh!

Copilot AI commented Jan 15, 2026

Uh oh!

Ruochun commented Jan 15, 2026

Uh oh!

Copilot AI commented Jan 15, 2026

Uh oh!

Ruochun commented Jan 15, 2026

Package Plan

Package Plan

Uh oh!

Copilot AI commented Jan 15, 2026

Uh oh!

Ruochun commented Jan 15, 2026

Package Plan

Package Plan

Uh oh!

Copilot AI commented Jan 15, 2026

Uh oh!

Ruochun commented Jan 15, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Copilot AI commented Jan 5, 2026 •

edited

Loading