Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix performance issue introduced by torch cuda cache clear during generation

Browse Source
This commit is contained in:
Kyle Schouviller 2022-11-10 21:43:56 -08:00
parent 4b4111a802
commit 8dc7f119e5
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ldm/modules/attention.py
View File

@ -282,7 +282,6 @@ class CrossAttention(nn.Module):
def get_attention_mem_efficient(self, q, k, v):
if q.device.type == 'cuda':
torch.cuda.empty_cache()
#print("in get_attention_mem_efficient with q shape", q.shape, ", k shape", k.shape, ", free memory is", get_mem_free_total(q.device))
return self.einsum_op_cuda(q, k, v)