llama : add check for KV cache shifts (#10401)

ggml-ci
This commit is contained in:
Georgi Gerganov authored and GitHub committed 2024-11-19 13:29:26 +02:00
1 parent a88ad007de
commit 8e752a777b
3 files changed
+14 -1

No files matched your search

+3
View File
@@ -667,6 +667,9 @@ extern "C" {
// Apply the KV cache updates (such as K-shifts, defragmentation, etc.)
LLAMA_API void llama_kv_cache_update(struct llama_context * ctx);
// Check if the context supports KV cache shifting
LLAMA_API bool llama_kv_cache_can_shift(struct llama_context * ctx);
//
// State / sessions
//