mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-11 10:36:54 +00:00
context : prepare kv_cache_read/write to be moved to kv_cache
ggml-ci
This commit is contained in:
@@ -44,6 +44,7 @@ struct llama_kv_cache_slot_info {
|
||||
|
||||
// ring-buffer of cached KV data
|
||||
// TODO: pimpl
|
||||
// TODO: add notion of max sequences
|
||||
struct llama_kv_cache {
|
||||
bool has_shift = false;
|
||||
bool do_defrag = false;
|
||||
|
||||
Reference in New Issue
Block a user