This PR is ready for review.
Tagging @CISC and @slaren— your feedback would be greatly appreciated whenever you have the chance.
Thanks for your work on maintaining and improving the CUDA backend!

Unfortunately, the reason no backends support CONV_3D is that ggml_conv_3d uses the IM2COL_3D op instead. This is an unused op.

There also exists #16948 . You can use the conv3d test program from that pr to compare the performance.

Thanks for the review and the clarification!

If it makes sense for the project, I can follow up with a small PR that adds
optional graph support for GGML_OP_CONV_3D. The idea would be:

• keep the existing IM2COL_3D + MUL_MAT lowering as the default path
• allow backends that explicitly report Conv3D support to receive a native
Conv3D node
• measure the performance impact on CUDA (memory footprint, bandwidth,
end-to-end time)

If the benchmarks show clear benefits for Conv3D on supported backends, then
enabling the native path in more scenarios could be considered. Otherwise,
the fallback path remains unchanged.

This keeps behavior stable while opening the door for backend-level
optimizations, without committing the project to any change in graph
lowering.

Let me know if this direction sounds reasonable — happy to iterate.