Skip to content

Can you provide new wheels for custom_rasterizer and mesh_inpaint_processor in the dist folders? #74

@ELiZswe

Description

@ELiZswe

With the latest version of comfyui, the

comfyui Version: v0.16.4 Portable
Torch: 2.10.1
Cuda: 13.0
Python 3.13.1

I've been able to compile mesh_inpaint_processor myself.(I'll paste a link to that when I get back later today)
I've found custom_rasterizer for 2.9.1 here:
https://huggingface.co/TheArtOfficialTrainer/CustomRasterizerWheels/tree/main

Bu that requires downgrading Torch to 2.9.1:
.\ComfyUI_windows_portable\python_embeded\python.exe -m pip install torch==2.9.1 torchvision==0.24.1 torchaudio==2.9.1 --index-url https://download.pytorch.org/whl/cu130

And so far everything seem to work, but the downgrade will most likely make other stuff in Comfyui to stop working, so it would be great to get precompiled wheels in this module directly.
I've neven been able to get compiling of custom_rasterizer to work, and always has been reliant on others

From startup:

pytorch version: 2.9.1+cu130
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 28391.0
working around nvidia conv3d memory bug.
Using pytorch attention
aimdo: src-win/cuda-detour.c:77:INFO:aimdo_setup_hooks: found driver at 00007FFFB2CC0000, installing 4 hooks
aimdo: src-win/cuda-detour.c:61:DEBUG:install_hook_entrys: hooks successfully installed
aimdo: src/control.c:66:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 5090 (VRAM: 32606 MB)
DynamicVRAM support detected and enabled
Python version: 3.13.11 (tags/v3.13.11:6278944, Dec  5 2025, 16:26:58) [MSC v.1944 64 bit (AMD64)]
ComfyUI version: 0.16.4
ComfyUI frontend version: 1.39.19

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions