From 028d3f6425d85f122027c127fba8bcbf4f66ee75 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 10 May 2023 11:05:02 +0300
Subject: ruff auto fixes

---
 modules/devices.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'modules/devices.py')

diff --git a/modules/devices.py b/modules/devices.py
index c705a3cb..d8a34a0f 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -65,7 +65,7 @@ def enable_tf32():
 
         # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
         # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
-        if any([torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())]):
+        if any(torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())):
             torch.backends.cudnn.benchmark = True
 
         torch.backends.cuda.matmul.allow_tf32 = True
-- 
cgit v1.2.1


From 8faac8b96313c6c4bf0a81bddecff4d6ba22ac25 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sun, 21 May 2023 21:55:14 +0300
Subject: run basic torch calculation at startup in parallel to reduce the
 performance impact of first generation

---
 modules/devices.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'modules/devices.py')

diff --git a/modules/devices.py b/modules/devices.py
index d8a34a0f..1ed6ffdc 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -1,5 +1,7 @@
 import sys
 import contextlib
+from functools import lru_cache
+
 import torch
 from modules import errors
 
@@ -154,3 +156,19 @@ def test_for_nans(x, where):
     message += " Use --disable-nan-check commandline argument to disable this check."
 
     raise NansException(message)
+
+
+@lru_cache
+def first_time_calculation():
+    """
+    just do any calculation with pytorch layers - the first time this is done it allocaltes about 700MB of memory and
+    spends about 2.7 seconds doing that, at least wih NVidia.
+    """
+
+    x = torch.zeros((1, 1)).to(device, dtype)
+    linear = torch.nn.Linear(1, 1).to(device, dtype)
+    linear(x)
+
+    x = torch.zeros((1, 1, 3, 3)).to(device, dtype)
+    conv2d = torch.nn.Conv2d(1, 1, (3, 3)).to(device, dtype)
+    conv2d(x)
-- 
cgit v1.2.1