kv-cache : fix find_slot to not search for continuous slot (#15638)

ggml-ci

diff --git a/src/llama-kv-cache.cpp b/src/llama-kv-cache.cpp
index 4485f78d5f5330bacac182aec38cd884583cf3ab..f1c6918738684c1ace92fa7c010a437423791abc 100644 (file)
--- a/src/llama-kv-cache.cpp
+++ b/src/llama-kv-cache.cpp
@@ -540,7 +540,7 @@ llama_kv_cache::slot_info_vec_t llama_kv_cache::prepare(const std::vector<llama_
 
     for (const auto & ubatch : ubatches) {
         // only find a suitable slot for the ubatch. don't modify the cells yet
-        const auto sinfo_new = find_slot(ubatch, true);
+        const auto sinfo_new = find_slot(ubatch, false);
         if (sinfo_new.empty()) {
             success = false;
             break;