dev-python/spconv-cu126
Spatially sparse convolution library (prebuilt cu126 wheel)
Screenshots
View
Download
BrowseChangeLog
commit 0419e475502f7acc4ae0ff6bb39a06fbe28c711b
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu Sep 10 07:07:53 2026 +0200
dev-python/spconv-cu126: declare 2.3.8 wheel installer
Wheel extraction uses the installer module during the build, so it
must be declared instead of supplied incidentally.
commit 7ee91d5bd6fc089e4a96934246726beb874b54be
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Aug 14 17:36:34 2026 +0200
dev-python/spconv-cu126: complete wheel dependencies
The 2.3.8 wheel metadata requires minimum pccm, ccimport, and pybind11 versions and
declares fire for its shipped command paths. Mirror those requirements and keep the
compatibility rationale portable.
commit 8b8c76e6f381d572c8da9b5e10ab677376ee357b
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Wed Jun 17 10:08:32 2026 +0200
dev-python/spconv-cu126: new package, add 2.3.8
Sparse-convolution backend for the TRELLIS image-to-3D node. The TRELLIS
pretrained weights use spconv's weight naming and layout, so spconv (not
torchsparse) is the backend that can load them. The cu126 binary wheel bundles
its own CUDA kernels via cumm and does not link libtorch, so it runs against
this host's CUDA 13.3 / torch 2.11 stack. cumm is capped <0.8.0 by upstream.
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu Sep 10 07:07:53 2026 +0200
dev-python/spconv-cu126: declare 2.3.8 wheel installer
Wheel extraction uses the installer module during the build, so it
must be declared instead of supplied incidentally.
commit 7ee91d5bd6fc089e4a96934246726beb874b54be
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri Aug 14 17:36:34 2026 +0200
dev-python/spconv-cu126: complete wheel dependencies
The 2.3.8 wheel metadata requires minimum pccm, ccimport, and pybind11 versions and
declares fire for its shipped command paths. Mirror those requirements and keep the
compatibility rationale portable.
commit 8b8c76e6f381d572c8da9b5e10ab677376ee357b
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Wed Jun 17 10:08:32 2026 +0200
dev-python/spconv-cu126: new package, add 2.3.8
Sparse-convolution backend for the TRELLIS image-to-3D node. The TRELLIS
pretrained weights use spconv's weight naming and layout, so spconv (not
torchsparse) is the backend that can load them. The cu126 binary wheel bundles
its own CUDA kernels via cumm and does not link libtorch, so it runs against
this host's CUDA 13.3 / torch 2.11 stack. cumm is capped <0.8.0 by upstream.