What are you trying to do?
I am trying to Run LTX2.3 but dynamic Vram is disabled, I believe due to the below warning about pytorch version
[WARNING] Unsupported Pytorch detected. DynamicVRAM support requires Pytorch version 2.8 or later. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows
[INFO] Python version: 3.10.20 | packaged by conda-forge | (main, Jun 11 2026, 03:28:51) [MSC v.1944 64 bit (AMD64)]
[INFO] pytorch version: 2.7.0+cu128
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 25948.0
[INFO] Using pytorch attention
What have you tried?
I tried manually updating Pytorch, but ran out of talent and had to fresh install.
Your system (OS / GPU / RAM / VRAM / etc.)
Windows 11
RTX 5090
RAM 64GB
VRAM 32GB
How do I solve this, thanks.
What are you trying to do?
I am trying to Run LTX2.3 but dynamic Vram is disabled, I believe due to the below warning about pytorch version
[WARNING] Unsupported Pytorch detected. DynamicVRAM support requires Pytorch version 2.8 or later. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows
[INFO] Python version: 3.10.20 | packaged by conda-forge | (main, Jun 11 2026, 03:28:51) [MSC v.1944 64 bit (AMD64)]
[INFO] pytorch version: 2.7.0+cu128
[INFO] Set vram state to: NORMAL_VRAM
[INFO] Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
[INFO] Using async weight offloading with 2 streams
[INFO] Enabled pinned memory 25948.0
[INFO] Using pytorch attention
What have you tried?
I tried manually updating Pytorch, but ran out of talent and had to fresh install.
Your system (OS / GPU / RAM / VRAM / etc.)
Windows 11
RTX 5090
RAM 64GB
VRAM 32GB
How do I solve this, thanks.