because of #9031, don't need --disable-cuda-malloc

This commit is contained in:
hongliang.yuan 2025-07-24 10:16:50 +08:00
parent 5e81cc00fc
commit 328034076c

View File

@ -299,9 +299,7 @@ For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a
For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method: For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:
1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the [Installation](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536) 1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the [Installation](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536)
2. Launch ComfyUI by running `python main.py --disable-cuda-malloc` 2. Launch ComfyUI by running `python main.py`
> **Note**: Due to limited support for cudaMallocAsync, so add `--disable-cuda-malloc` for compatibility.
# Running # Running