New discussion

Error serving GGUF models on vllm

5
#7 opened about 1 month ago by maveriq

6 part

#5 opened 2 months ago by goodasdgood

split

3
#4 opened 2 months ago by goodasdgood

it run on colab cpu

#3 opened 2 months ago by goodasdgood

multi-part model

8
#2 opened 2 months ago by goodasdgood

vram usage of each?

3
#1 opened 2 months ago by jasonden