SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Paper
•
2411.05007
•
Published
•
19
•
3
Muyang Li
Lmxyy
AI & ML interests
None yet
Recent Activity
updated
a model
about 4 hours ago
mit-han-lab/nunchaku-artifacts
updated
a model
about 5 hours ago
mit-han-lab/nunchaku-test-models
published
a model
about 5 hours ago
mit-han-lab/nunchaku-test-models
Organizations
Lmxyy's activity
Could have a win support .whl file for python 3.10+torch2.5?
🔥
1
3
#1 opened 3 months ago
by
DragAIxxx
Use with Diffusers
6
#9 opened 10 months ago
by
HaileyStorm
How is this flux dev different from the last one?
1
#1 opened 14 days ago
by
pheonis
Has the RTX50 series been adapted?
1
#3 opened 16 days ago
by
YEXIN413
We need nunchaku 0.3.0 wheel file,thank you
➕
5
2
#3 opened 24 days ago
by
like8522
awq_update
#3 opened 28 days ago
by
Aprilhuuu
why does this include the full t5 fp16 model alongside the svdq-t5.safetensors
1
#4 opened 23 days ago
by
tazztone
Update quantized t5 model
1
#2 opened about 2 months ago
by
Aprilhuuu
🚩 Report: Copyright infringement
1
#3 opened about 2 months ago
by
w107584546
possible ipadapter support?
1
#2 opened 2 months ago
by
reverentelusarca
What is this model used for?
1
#1 opened 4 months ago
by
remember2015
Can't wait to experience it in comfyui
2
#1 opened 6 months ago
by
zhaoqi
commented
2
papers
7 months ago
Cannot install mixdq
2
#1 opened about 1 year ago
by
Lmxyy