batched inference with video input
#11 opened 1 day ago
by
vexilligera
Looking Forward to models in GPTQModel formats like W4A16 and W8A16
#10 opened 16 days ago
by
X-SZM
afs
#8 opened 22 days ago
by
Marc-Anthony

Bitsandbytesconfig 4bit possible?
#6 opened 27 days ago
by
Day1Kim
zai-org/GLM-4.5V not working in sglang please help. I have 8xh100
#5 opened 28 days ago
by
dahwinsingularity

LoRA adapter?
#3 opened 29 days ago
by
lightenup
A look into the future: Wishlist for GLM-5
👍
11
4
#2 opened 29 days ago
by
Dampfinchen
Text performance compared to GLM-4.5 Air
👀
4
2
#1 opened 29 days ago
by
Dampfinchen