batched : add bench tool (#3545)

* batched : add bench tool

* batched : minor fix table

* batched-bench : add readme + n_kv_max is now configurable

* batched-bench : init warm-up batch

* batched-bench : pass custom set of PP, TG and PL

* batched-bench : add mmq CLI arg

1 files changed, 1 insertions, 1 deletions

diff --git a/examples/batched/batched.cpp b/examples/batched/batched.cpp
index 688ef221..a88e022d 100644
--- a/examples/batched/batched.cpp
+++ b/examples/batched/batched.cpp
@@ -66,7 +66,7 @@ int main(int argc, char ** argv) {
     ctx_params.seed  = 1234;
     ctx_params.n_ctx = n_kv_req;
     ctx_params.n_batch = std::max(n_len, n_parallel);
-    ctx_params.n_threads = params.n_threads;
+    ctx_params.n_threads       = params.n_threads;
     ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
 
     llama_context * ctx = llama_new_context_with_model(model, ctx_params);