llama.cpp
server : add `n_discard` parameter to specify the number of tokens to discard when context is shifted
#6300
Merged
Merged
server : add `n_discard` parameter to specify the number of tokens to discard when context is shifted #6300
ggerganov
merged
1 commit into
ggml-org:master
from
kaetemi:feature/server-ndiscard-param
Login to write a write a comment.
Login via GitHub