andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Clear cache as often on AMD as Nvidia.

Browse Source 
I think the issue this was working around has been solved.

If you notice that this change slows things down or causes stutters on
your AMD GPU with ROCm on Linux please report it.
This commit is contained in:
comfyanonymous
2025-01-02 08:44:16 -05:00
parent 0f11d60afb
commit 9e9c8a1c64
1 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
comfy/model_management.py
View File

@@ -1121,9 +1121,8 @@ def soft_empty_cache(force=False):
elif is_ascend_npu():
torch.npu.empty_cache()
elif torch.cuda.is_available():
if force or is_nvidia(): #This seems to make things worse on ROCm so I only do it for cuda
torch.cuda.empty_cache()
torch.cuda.ipc_collect()
torch.cuda.empty_cache()
torch.cuda.ipc_collect()
def unload_all_models():
free_memory(1e30, get_torch_device())