A Dujari PRO
ovedrive
AI & ML interests
Unnecessarily LLM - make AI/ML run on potatoes
Organizations
call vllm or sglang?
4
#2 opened 2 months ago
by
zhnagchenchne
torch 2.9 issue
3
#1 opened 9 months ago
by
faheemraza1
request for generation steps
1
#5 opened 7 months ago
by
kartikvyas1
how to acceleration
1
#4 opened 8 months ago
by
liujian1991
Thanks!
#3 opened 9 months ago
by
Clifton100
Thank you! This is the second quant i've used of yours :)
👍 1
5
#1 opened 9 months ago
by
mtecnic
Some Sort of OOM issue.
1
#2 opened 9 months ago
by
KaiPG
Does this support Lightning LoRAs?
4
#1 opened 9 months ago
by
MinhNH232331M
Is this an uncensored version?
1
#2 opened 10 months ago
by
Lobliqua
[solved] CUDA OOM with RTX 5060 Ti 16G
3
#5 opened 11 months ago
by
foxedge
Newer Model
1
#4 opened about 1 year ago
by
faheemraza1
Merged text encoder?
1
#1 opened about 1 year ago
by
Kamikaze-88
LoRA training
1
#3 opened about 1 year ago
by
faheemraza1
Permanent residence in VRAM
6
#5 opened about 1 year ago
by
rtbonet
Thanks this now works with new bnb model loader in comfyUI
👍 1
1
#2 opened about 1 year ago
by
mengqin1
How to run on 16GB VRAM
13
#4 opened about 1 year ago
by
aahila
Qwen Image Edit + ControlNet Openpose is possible?
1
#3 opened about 1 year ago
by
asdasdasdwd
how to use it
3
#1 opened about 1 year ago
by
yangsheng123
the result is a all black image ?
4
#2 opened about 1 year ago
by
zet-yd
[Request] Qwen-image-edit-4bit
2
#1 opened about 1 year ago
by
jspsoli