llama : fix session saving/loading (#3400)

* llama : fix session saving/loading

* llama : temp fix for clearing "future" tokens from the KV cache

* llama : fix handling of "future" tokens when loading sessions

* llama : fix comments for llama_kv_cache API

1 files changed, 1 insertions, 1 deletions

diff --git a/examples/parallel/parallel.cpp b/examples/parallel/parallel.cpp
index 0434ded2..ffd7b1db 100644
--- a/examples/parallel/parallel.cpp
+++ b/examples/parallel/parallel.cpp
@@ -332,7 +332,7 @@ int main(int argc, char ** argv) {
                     }
 
                     // delete only the generated part of the sequence, i.e. keep the system prompt in the cache
-                    llama_kv_cache_seq_rm(ctx, client.id, n_tokens_system, n_ctx);
+                    llama_kv_cache_seq_rm(ctx, client.id, n_tokens_system, -1);
 
                     const auto t_main_end = ggml_time_us();