Skip to content

GitLab

Commit dce35553 authored by comfyanonymous's avatar comfyanonymous
Browse files

Add some tesla pascal GPUs to the fp16 working but slower list.

parent 51df8465
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
comfy/model_management.py
View file @ dce35553
...@@ -753,7 +753,7 @@ def should_use_fp16(device=None, model_params=0, prioritize_performance=True, ma ...@@ -753,7 +753,7 @@ def should_use_fp16(device=None, model_params=0, prioritize_performance=True, ma
#FP16 is confirmed working on a 1080 (GP104) but it's a bit slower than FP32 so it should only be enabled #FP16 is confirmed working on a 1080 (GP104) but it's a bit slower than FP32 so it should only be enabled
#when the model doesn't actually fit on the card #when the model doesn't actually fit on the card
#TODO: actually test if GP106 and others have the same type of behavior #TODO: actually test if GP106 and others have the same type of behavior
nvidia_10_series = ["1080", "1070", "titan x", "p3000", "p3200", "p4000", "p4200", "p5000", "p5200", "p6000", "1060", "1050"] nvidia_10_series = ["1080", "1070", "titan x", "p3000", "p3200", "p4000", "p4200", "p5000", "p5200", "p6000", "1060", "1050", "p40", "p100", "p6", "p4"]
for x in nvidia_10_series: for x in nvidia_10_series:
if x in props.name.lower(): if x in props.name.lower():
fp16_works = True fp16_works = True
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment