hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-04 03:10:21 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add InvokeAI and lstein to credits, add back CUDA support

Browse Source
This commit is contained in:
brkirch
2022-10-11 03:32:11 -04:00
committed by AUTOMATIC1111
parent 98fd5cde72
commit 574c8e554a
2 changed files with 14 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
modules/sd_hijack_optimizations.py
View File

@@ -173,7 +173,20 @@ def einsum_op_tensor_mem(q, k, v, max_tensor_mb):
return einsum_op_slice_0(q, k, v, q.shape[0] // div)
return einsum_op_slice_1(q, k, v, max(q.shape[1] // div, 1))
def einsum_op_cuda(q, k, v):
stats = torch.cuda.memory_stats(q.device)
mem_active = stats['active_bytes.all.current']
mem_reserved = stats['reserved_bytes.all.current']
mem_free_cuda, _ = torch.cuda.mem_get_info(q.device)
mem_free_torch = mem_reserved - mem_active
mem_free_total = mem_free_cuda + mem_free_torch
# Divide factor of safety as there's copying and fragmentation
return self.einsum_op_tensor_mem(q, k, v, mem_free_total / 3.3 / (1 << 20))
def einsum_op(q, k, v):
if q.device.type == 'cuda':
return einsum_op_cuda(q, k, v)
if q.device.type == 'mps':
if mem_total_gb >= 32:
return einsum_op_mps_v1(q, k, v)