refact : fix convert script + zero out KV cache to avoid nans (#3523)

* refact : fix convert script + zero out KV cache to avoid nans

* ggml : silu(-inf) should never happen

* metal : assert various kernel requirements

1 files changed, 1 insertions, 1 deletions

diff --git a/examples/parallel/parallel.cpp b/examples/parallel/parallel.cpp
index 721888da..04f1e45b 100644
--- a/examples/parallel/parallel.cpp
+++ b/examples/parallel/parallel.cpp
@@ -167,7 +167,7 @@ int main(int argc, char ** argv) {
 
     // the max batch size is as large as the context to handle cases where we get very long input prompt from multiple
     // users. regardless of the size, the main loop will chunk the batch into a maximum of params.n_batch tokens at a time
-    llama_batch batch = llama_batch_init(params.n_ctx, 0);
+    llama_batch batch = llama_batch_init(n_ctx, 0);
 
     int32_t n_total_prompt = 0;
     int32_t n_total_gen    = 0;