aboutsummaryrefslogtreecommitdiff
path: root/modules/devices.py
diff options
context:
space:
mode:
Diffstat (limited to 'modules/devices.py')
-rw-r--r--modules/devices.py5
1 files changed, 3 insertions, 2 deletions
diff --git a/modules/devices.py b/modules/devices.py
index c01f0602..f97f9cfb 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -38,7 +38,7 @@ def get_optimal_device():
def get_device_for(task):
- if task in shared.cmd_opts.use_cpu:
+ if task in shared.cmd_opts.use_cpu or "all" in shared.cmd_opts.use_cpu:
return cpu
return get_optimal_device()
@@ -60,7 +60,8 @@ 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())):
+ device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()
+ if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"):
torch.backends.cudnn.benchmark = True
torch.backends.cuda.matmul.allow_tf32 = True