context : clear sets containing encoder output sequence ids before storing new values...

Co-authored-by: Stanisław Szymczyk <redacted>

diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index 664703a896701a9988a23fd79405f00154622bb0..5bec63e2e79ff81fde3fa2ed12fbbfc32ea8bca5 100644 (file)
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -1153,6 +1153,7 @@ int llama_context::encode(llama_batch & inp_batch) {
         // remember the sequence ids used during the encoding - needed for cross attention later
         cross.seq_ids_enc.resize(n_tokens);
         for (int32_t i = 0; i < n_tokens; i++) {
+            cross.seq_ids_enc[i].clear();
             for (int s = 0; s < ubatch.n_seq_id[i]; s++) {
                 llama_seq_id seq_id = ubatch.seq_id[i][s];
                 cross.seq_ids_enc[i].insert(seq_id);