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, 3 insertions, 0 deletions

diff --git a/examples/main/main.cpp b/examples/main/main.cpp
index 3a4ed3f7..7367ae36 100644
--- a/examples/main/main.cpp
+++ b/examples/main/main.cpp
@@ -543,6 +543,9 @@ int main(int argc, char ** argv) {
                 if (i > 0) {
                     embd.erase(embd.begin(), embd.begin() + i);
                 }
+
+                // remove any "future" tokens that we might have inherited from the session from the KV cache
+                llama_kv_cache_tokens_rm(ctx, n_past, -1);
             }
 
             // evaluate tokens in batches