llama.cpp
Extend llama_kv_cache_seq_rm to allow matching any sequence
#3843

Merged

Commits

Extend llama_kv_cache_seq_rm to allow matichng any sequence

KerfuffleV2 committed 1 year ago
Replace llama_kv_cache_tokens_rm with llama_kv_cache_clear

KerfuffleV2 committed 1 year ago

Loading