Extend llama_kv_cache_seq_rm to allow matching any sequence #3843
KerfuffleV2
merged
2 commits into
ggml-org:master
from
KerfuffleV2:feat-kv_seq_rm_wildcard
Extend llama_kv_cache_seq_rm to allow matichng any sequence
ebd4b913
ggerganov
approved these changes
on 2023-10-29
Replace llama_kv_cache_tokens_rm with llama_kv_cache_clear
bed3f179
KerfuffleV2
commented
on 2023-10-29
ggerganov
approved these changes
on 2023-10-29
Login to write a write a comment.
Login via GitHub