metal : pad n_ctx by 32 (#6177)

* metal : require ne00 >= 128 for mat-mat kernels

ggml-ci

* llama : pad n_ctx by 32

ggml-ci

1 files changed, 3 insertions, 1 deletions

diff --git a/examples/batched/batched.cpp b/examples/batched/batched.cpp
index ee1f8f1b..7aaf63ce 100644
--- a/examples/batched/batched.cpp
+++ b/examples/batched/batched.cpp
@@ -48,6 +48,8 @@ int main(int argc, char ** argv) {
         params.prompt = "Hello my name is";
     }
 
+    process_escapes(params.prompt);
+
     // init LLM
 
     llama_backend_init();
@@ -78,7 +80,7 @@ int main(int argc, char ** argv) {
     llama_context_params ctx_params = llama_context_default_params();
 
     ctx_params.seed  = 1234;
-    ctx_params.n_ctx = n_kv_req;
+    ctx_params.n_ctx   = n_kv_req;
     ctx_params.n_batch = std::max(n_len, n_parallel);
     ctx_params.n_seq_max       = n_parallel;
     ctx_params.n_threads       = params.n_threads;