xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2026-08-16 10:56:37 +08:00
Code Issues 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 c93c54d7d5
commit 7ce8ef2b20
1 changed files with 2 additions and 3 deletions
Show Stats 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())