Hugging Face's logo

benew666
/
Nunchaku_OOM_Fix

Model card Files
xet
 Community
benew666 commited on
Commit
cc9902a
·
verified ·
1 Parent(s): 68c456e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ license: mit
12
  This patch addresses critical CUDA out of memory errors occurring in ComfyUI-nunchaku on high-VRAM GPUs (14GB+).
13
 
14
  ## Problem Solved
15
- CUDA error: out of memory (at C:\Users\muyangl\actions-runner_work\nunchaku\nunchaku\src\Tensor.h:95
16
  - **Issue:** Nunchaku automatically disables CPU offload for GPUs with ≥14GB VRAM
17
  - **Impact:** CUDA OOM errors despite sufficient VRAM
18
  - **Affected GPUs:** RTX 3090 (24GB), RTX 4080 (16GB), RTX 4090 (24GB), and similar
 
12
  This patch addresses critical CUDA out of memory errors occurring in ComfyUI-nunchaku on high-VRAM GPUs (14GB+).
13
 
14
  ## Problem Solved
15
+ CUDA error: out of memory (at C:\Users\muyangl\actions-runner_work\nunchaku\nunchaku\src\Tensor.h:95)
16
  - **Issue:** Nunchaku automatically disables CPU offload for GPUs with ≥14GB VRAM
17
  - **Impact:** CUDA OOM errors despite sufficient VRAM
18
  - **Affected GPUs:** RTX 3090 (24GB), RTX 4080 (16GB), RTX 4090 (24GB), and similar