Ernest Yeung
ernestyalumni
AI & ML interests
I'm interested in developing models directly in CUDA C++ or libNVVM. Reach out to me if you share the same interest!
Organizations
ernestyalumni's activity
Missing config.json?
2
#5 opened 27 days ago
by
ernestyalumni
Python Script to run it below 16GB vram
8
#50 opened 3 months ago
by
snapo
How to speed up model generation
3
#13 opened about 2 months ago
by
LiPengtao12138
Passing in data via function calls
2
#18 opened about 2 months ago
by
thegamecat
Error when evaluate this model using pipeline
2
#13 opened about 2 months ago
by
xiaxin1998
Examples of usage
5
#14 opened about 2 months ago
by
ernestyalumni
Warning: The attention mask and the pad token id were not set..
4
#40 opened 7 months ago
by
Stephen-smj
md5sums of files
#10 opened about 2 months ago
by
ernestyalumni
CUDA out of memory
8
#37 opened 3 months ago
by
TheAlphaGhost
Just amazing results.
3
#47 opened 3 months ago
by
TashaSkyUp
Does this support image to image generation?
6
#23 opened 4 months ago
by
pck2123
VRAM req
9
#5 opened 4 months ago
by
linitini
Flux for 8GB graphics card
6
#17 opened 4 months ago
by
xxMegalo