kv_cache management

examples/lookup/lookup.cpp

@@ -130,6 +130,10 @@ int main(int argc, char ** argv){
             break;
         }
 
+        // KV cache management
+        // clean the cache of draft tokens that weren't accepted
+        llama_kv_cache_seq_rm(ctx, 0, n_past, -1);
+
         llama_batch_clear(batch_tgt);
         llama_batch_add(batch_tgt, draft[0], n_past, { 0 }, true);