llama.cpp
llama-diffusion-cli: read n_ctx back after making llama_context so the cli doesn't reject all input without -c
#21939
Merged
Merged
llama-diffusion-cli: read n_ctx back after making llama_context so the cli doesn't reject all input without -c #21939
am17an
merged
1 commit into
ggml-org:master
from
smashedpumpkin:master
Login to write a write a comment.
Login via GitHub