Sign inSign up
M

mxxm

Community User

Displaying 1 to 2 of 2 repositories

image

Latest vanilla llama.cpp for gfx906

3d

100K+

3

image

Slim ROCm 7.2.1 llama.cpp for AMD gfx906 (MI50/Vega20): multi-GPU tensor-parallel + MTP, ~1.5GB

15d

10K+

5