nvdiffrast wheel for torch 2.8.0+cu128 (Python 3.12, Linux), its license and build script

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wheels/nvdiffrast-0.4.0+pt2.8.0cu128-cp312-cp312-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text

NVDIFFRAST_LICENSE.txt

@@ -0,0 +1,97 @@
+Copyright (c) 2020, NVIDIA Corporation. All rights reserved.
+
+
+Nvidia Source Code License (1-Way Commercial)
+
+=======================================================================
+
+1. Definitions
+
+"Licensor" means any person or entity that distributes its Work.
+
+"Software" means the original work of authorship made available under
+this License.
+
+"Work" means the Software and any additions to or derivative works of
+the Software that are made available under this License.
+
+The terms "reproduce," "reproduction," "derivative works," and
+"distribution" have the meaning as provided under U.S. copyright law;
+provided, however, that for the purposes of this License, derivative
+works shall not include works that remain separable from, or merely
+link (or bind by name) to the interfaces of, the Work.
+
+Works, including the Software, are "made available" under this License
+by including in or with the Work either (a) a copyright notice
+referencing the applicability of this License to the Work, or (b) a
+copy of this License.
+
+2. License Grants
+
+    2.1 Copyright Grant. Subject to the terms and conditions of this
+    License, each Licensor grants to you a perpetual, worldwide,
+    non-exclusive, royalty-free, copyright license to reproduce,
+    prepare derivative works of, publicly display, publicly perform,
+    sublicense and distribute its Work and any resulting derivative
+    works in any form.
+
+3. Limitations
+
+    3.1 Redistribution. You may reproduce or distribute the Work only
+    if (a) you do so under this License, (b) you include a complete
+    copy of this License with your distribution, and (c) you retain
+    without modification any copyright, patent, trademark, or
+    attribution notices that are present in the Work.
+
+    3.2 Derivative Works. You may specify that additional or different
+    terms apply to the use, reproduction, and distribution of your
+    derivative works of the Work ("Your Terms") only if (a) Your Terms
+    provide that the use limitation in Section 3.3 applies to your
+    derivative works, and (b) you identify the specific derivative
+    works that are subject to Your Terms. Notwithstanding Your Terms,
+    this License (including the redistribution requirements in Section
+    3.1) will continue to apply to the Work itself.
+
+    3.3 Use Limitation. The Work and any derivative works thereof only
+    may be used or intended for use non-commercially. The Work or
+    derivative works thereof may be used or intended for use by Nvidia
+    or its affiliates commercially or non-commercially. As used herein,
+    "non-commercially" means for research or evaluation purposes only
+    and not for any direct or indirect monetary gain.
+
+    3.4 Patent Claims. If you bring or threaten to bring a patent claim
+    against any Licensor (including any claim, cross-claim or
+    counterclaim in a lawsuit) to enforce any patents that you allege
+    are infringed by any Work, then your rights under this License from
+    such Licensor (including the grant in Section 2.1) will terminate
+    immediately.
+
+    3.5 Trademarks. This License does not grant any rights to use any
+    Licensor's or its affiliates' names, logos, or trademarks, except
+    as necessary to reproduce the notices described in this License.
+
+    3.6 Termination. If you violate any term of this License, then your
+    rights under this License (including the grant in Section 2.1) will
+    terminate immediately.
+
+4. Disclaimer of Warranty.
+
+THE WORK IS PROVIDED "AS IS" WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR
+NON-INFRINGEMENT. YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER
+THIS LICENSE.
+
+5. Limitation of Liability.
+
+EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL
+THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE
+SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT,
+INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF
+OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK
+(INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION,
+LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER
+COMMERCIAL DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN ADVISED OF
+THE POSSIBILITY OF SUCH DAMAGES.
+
+=======================================================================

README.md

@@ -28,6 +28,7 @@ whole-body motion, after which a foot refinement module (FootMR) and a hand refi
 |---|---|---|
 | `exmr.safetensors` | ExMR model (EMA weights, 236 MB) | `8d3947310c30444ec59dae4662574d7a32bf83af30320eeac87146529ff2fda5` |
 | `rtmw-x_384x288_fp16.onnx` | RTMW-x 2D whole-body keypoint detector, FP16 (optional `--pose_backend rtmw`), see below | `957ddb5ed34576593a918b3e514003ab9cc85d037309b9a23d9e0209530e98ed` |
+| `wheels/nvdiffrast-0.4.0+pt2.8.0cu128-cp312-cp312-linux_x86_64.whl` | nvdiffrast renderer for torch 2.8.0+cu128, Python 3.12, Linux (installed by ExMR's `docs/INSTALL.md`), see below | `ca26d44f4f198e8fb460f86f355c5fdaeaac6319e15a5551ea31397719c0d563` |
 
 ## Usage
 
@@ -77,6 +78,14 @@ onnx.save(float16.convert_float_to_float16(model, keep_io_types=True), "rtmw-x_3
 The only change is the conversion of the internal computations to FP16 (inputs and outputs stay
 FP32). We host it so that ExMR's results can be reproduced with exactly this file.
 
+`wheels/nvdiffrast-0.4.0+pt2.8.0cu128-cp312-cp312-linux_x86_64.whl` is a build of
+[nvdiffrast](https://github.com/NVlabs/nvdiffrast) v0.4.0 by NVIDIA, licensed under the NVIDIA
+Source Code License for non-commercial use (research or evaluation) only (see
+`NVDIFFRAST_LICENSE.txt` in this repository; the wheel contains it too). It is built from the
+unmodified v0.4.0 source (commit `253ac4f`; only the version label `+pt2.8.0cu128` is added) with
+`wheels/build_nvdiffrast_wheel.sh`: conda-forge nvcc 12.8 and gcc 14 against glibc 2.28, for the
+GPUs that torch 2.8.0+cu128 supports. We host it so that ExMR installs without compiling.
+
 ## Citation
 
 ```bibtex
@@ -90,4 +99,4 @@ FP32). We host it so that ExMR's results can be reproduced with exactly this fil
 
 Please also cite [GVHMR](https://github.com/zju3dv/GVHMR), which ExMR builds on, and the
 third-party models listed in the ExMR repository's
-[THIRD_PARTY_NOTICES.md](https://github.com/twehrbein/ExMR/blob/main/THIRD_PARTY_NOTICES.md).
+[THIRD_PARTY_NOTICES.md](https://github.com/twehrbein/ExMR/blob/main/THIRD_PARTY_NOTICES.md).

wheels/build_nvdiffrast_wheel.sh

@@ -0,0 +1,48 @@
+#!/bin/bash
+# Build the nvdiffrast v0.4.0 wheel for ExMR's torch (2.8.0+cu128, Python 3.12, Linux x86_64), so
+# that users install it without a compiler (ExMR's docs/INSTALL.md). Needs only conda (Miniforge):
+#
+#   bash build_nvdiffrast_wheel.sh <out dir>
+#
+# The wheel works on every Linux that torch 2.8 supports: it is built against glibc 2.28's headers
+# (conda's sysroot_linux-64=2.28, the manylinux_2_28 baseline of the torch wheels), so it needs no
+# newer glibc than torch (checked 2026-10-23: GLIBC_2.14, GLIBCXX_3.4.21; imports and renders
+# under glibc 2.28). GPUs: torch's own list (RTX 40 runs the code built for 8.6).
+# The source is the unmodified v0.4.0 tag; only the version gets the local label +pt2.8.0cu128.
+set -eo pipefail
+OUT=$(realpath -m "${1:?usage: $0 <out dir>}")
+ENV=${ENV:-nvdiffrast-build}
+ARCHS="7.0;7.5;8.0;8.6;9.0;10.0;12.0"
+COMMIT=253ac4fcea7de5f396371124af597e6cc957bfae  # tag v0.4.0
+
+source "$(conda info --base)/etc/profile.d/conda.sh"
+conda create -y -n "$ENV" -c conda-forge python=3.12 sysroot_linux-64=2.28 \
+    cuda-version=12.8 cuda-nvcc cuda-cudart-dev cuda-cccl libcublas-dev libcusparse-dev \
+    libcusolver-dev ninja git
+conda activate "$ENV"  # sets CC/CXX to the environment's gcc
+export PYTHONNOUSERSITE=1
+pip install torch==2.8.0 --index-url https://download.pytorch.org/whl/cu128
+pip install setuptools wheel
+
+SRC=$(mktemp -d)
+git clone -q https://github.com/NVlabs/nvdiffrast.git "$SRC/nvdiffrast"
+git -C "$SRC/nvdiffrast" checkout -q "$COMMIT"
+sed -i 's/^version = "0.4.0"$/version = "0.4.0+pt2.8.0cu128"/' "$SRC/nvdiffrast/pyproject.toml"
+grep -n "^version" "$SRC/nvdiffrast/pyproject.toml"
+
+mkdir -p "$OUT"
+# the compiler packages set a default TORCH_CUDA_ARCH_LIST on activation: override it
+TORCH_CUDA_ARCH_LIST="$ARCHS" CUDA_HOME=$CONDA_PREFIX \
+    pip wheel --no-build-isolation --no-deps -w "$OUT" "$SRC/nvdiffrast"
+rm -rf "$SRC"
+
+WHL=$(ls "$OUT"/nvdiffrast-0.4.0+pt2.8.0cu128-*.whl)
+SO=$(mktemp -d)
+python -m zipfile -e "$WHL" "$SO"
+echo "== $WHL"
+echo "sha256: $(sha256sum "$WHL" | cut -d' ' -f1)"
+echo "glibc needed: $(objdump -T "$SO"/_nvdiffrast_c*.so | grep -o 'GLIBC_[0-9.]*' | sort -uV | tail -1)"
+echo "libstdc++ needed: $(objdump -T "$SO"/_nvdiffrast_c*.so | grep -o 'GLIBCXX_[0-9.]*' | sort -uV | tail -1)"
+command -v cuobjdump >/dev/null &&
+    echo "GPU code: $(cuobjdump --list-elf "$SO"/_nvdiffrast_c*.so | grep -o 'sm_[0-9]*' | sort -uV | tr '\n' ' ')"
+rm -rf "$SO"

wheels/nvdiffrast-0.4.0+pt2.8.0cu128-cp312-cp312-linux_x86_64.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca26d44f4f198e8fb460f86f355c5fdaeaac6319e15a5551ea31397719c0d563
+size 4132409