diff options
| author | brkirch <brkirch@users.noreply.github.com> | 2022-10-11 07:32:11 +0000 |
|---|---|---|
| committer | AUTOMATIC1111 <16777216c@gmail.com> | 2022-10-11 14:24:00 +0000 |
| commit | 574c8e554a5371eca2cbf344764cb241c6ec4efc (patch) | |
| tree | 61d10c398e4e7cd5d16ba249d7e6dc291b30dfcc /modules/sd_hijack_optimizations.py | |
| parent | 98fd5cde72d5bda1620ab78416c7828fdc3dc10b (diff) | |
| download | stable-diffusion-webui-gfx803-574c8e554a5371eca2cbf344764cb241c6ec4efc.tar.gz stable-diffusion-webui-gfx803-574c8e554a5371eca2cbf344764cb241c6ec4efc.tar.bz2 stable-diffusion-webui-gfx803-574c8e554a5371eca2cbf344764cb241c6ec4efc.zip | |
Add InvokeAI and lstein to credits, add back CUDA support
Diffstat (limited to 'modules/sd_hijack_optimizations.py')
| -rw-r--r-- | modules/sd_hijack_optimizations.py | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 2a4ac7e0..f006427f 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -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)
|