diff --git a/examples/batched-bench/batched-bench.cpp b/examples/batched-bench/batched-bench.cpp index dff6c68ec..22bc93bca 100644 --- a/examples/batched-bench/batched-bench.cpp +++ b/examples/batched-bench/batched-bench.cpp @@ -106,7 +106,7 @@ int main(int argc, char ** argv) { ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch; // ensure enough sequences are available - ctx_params.n_parallel = *std::max_element(n_pl.begin(), n_pl.end()); + ctx_params.n_seq_max = *std::max_element(n_pl.begin(), n_pl.end()); llama_context * ctx = llama_new_context_with_model(model, ctx_params); diff --git a/examples/batched/batched.cpp b/examples/batched/batched.cpp index dde4d5a06..ee1f8f1bf 100644 --- a/examples/batched/batched.cpp +++ b/examples/batched/batched.cpp @@ -80,7 +80,7 @@ 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_parallel = n_parallel; + ctx_params.n_seq_max = n_parallel; ctx_params.n_threads = params.n_threads; ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;