diff options
| author | AUTOMATIC1111 <16777216c@gmail.com> | 2023-09-09 09:33:37 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-09-09 09:33:37 +0300 |
| commit | 558baffa2c934e84eff1a6648b2b4f4c4eb25e2b (patch) | |
| tree | 1715892a36451c948b87fcf3a07205aed04447b4 /modules/devices.py | |
| parent | 4ebed495ed692fbd88b0b6f13670eab69faeca8c (diff) | |
| parent | 5681bf801664aa09fa02ab8b4e73f780d9563440 (diff) | |
Merge pull request #12924 from catboxanon/fix/cudnn
More accurate check for enabling cuDNN benchmark on 16XX cards
Diffstat (limited to 'modules/devices.py')
| -rw-r--r-- | modules/devices.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/modules/devices.py b/modules/devices.py index c01f0602..63c38eff 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -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.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 |