llama : fix defrag bugs + add parameter (#5735)

* llama : fix defrag bugs + enable by default

ggml-ci

* llama : add defrag_thold parameter

ggml-ci

* llama : cont

* llama : disable log message

ggml-ci

* llama : fix graph size check during defrag

1 files changed, 1 insertions, 0 deletions

diff --git a/llama.h b/llama.h
index 3ff77d5a..60416180 100644
--- a/llama.h
+++ b/llama.h
@@ -245,6 +245,7 @@ extern "C" {
         float    yarn_beta_fast;   // YaRN low correction dim
         float    yarn_beta_slow;   // YaRN high correction dim
         uint32_t yarn_orig_ctx;    // YaRN original context size
+        float    defrag_thold;     // defragment the KV cache if holes/size > thold, < 0 disabled (default)
 
         ggml_backend_sched_eval_callback cb_eval;
         void * cb_eval_user_data;