From 04f8641815bee928180e300e15502581d8a1d553 Mon Sep 17 00:00:00 2001 From: Xuan Son Nguyen Date: Thu, 13 Mar 2025 23:14:16 +0100 Subject: [PATCH] rm redundant llama_batch_ext_set_output_last --- examples/cvector-generator/cvector-generator.cpp | 1 - examples/llama-bench/llama-bench.cpp | 1 - examples/simple-chat/simple-chat.cpp | 1 - examples/simple/simple.cpp | 1 - 4 files changed, 4 deletions(-) diff --git a/examples/cvector-generator/cvector-generator.cpp b/examples/cvector-generator/cvector-generator.cpp index 13fa2c442..b3236ea85 100644 --- a/examples/cvector-generator/cvector-generator.cpp +++ b/examples/cvector-generator/cvector-generator.cpp @@ -344,7 +344,6 @@ static bool cb_eval(struct ggml_tensor * t, bool ask, void * user_data) { static bool get_hidden_layers(llama_context * ctx, std::vector & tokens) { llama_kv_self_clear(ctx); llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), tokens.size(), 0, 0, true)); - llama_batch_ext_set_output_last(batch.get()); if (llama_decode_ext(ctx, batch.get())) { fprintf(stderr, "%s : failed to eval\n", __func__); return false; diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 6a6ab4ab2..bf39134d0 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -1445,7 +1445,6 @@ static void test_prompt(llama_context * ctx, int n_prompt, int n_batch, int n_th tokens[i] = std::rand() % n_vocab; } llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), n_tokens, 0, 0, true)); - llama_batch_ext_set_output_last(batch.get()); llama_decode_ext(ctx, batch.get()); n_processed += n_tokens; } diff --git a/examples/simple-chat/simple-chat.cpp b/examples/simple-chat/simple-chat.cpp index 0c2d34d56..dbde1ee9e 100644 --- a/examples/simple-chat/simple-chat.cpp +++ b/examples/simple-chat/simple-chat.cpp @@ -110,7 +110,6 @@ int main(int argc, char ** argv) { // prepare a batch for the prompt llama_pos n_past = 0; llama_batch_ext * batch = llama_batch_ext_init_from_text(prompt_tokens.data(), prompt_tokens.size(), n_past, 0, true); - llama_batch_ext_set_output_last(batch); n_past += llama_batch_ext_get_n_tokens(batch); llama_token new_token_id; diff --git a/examples/simple/simple.cpp b/examples/simple/simple.cpp index 9101cc6bb..4aea9dbdc 100644 --- a/examples/simple/simple.cpp +++ b/examples/simple/simple.cpp @@ -144,7 +144,6 @@ int main(int argc, char ** argv) { // prepare a batch for the prompt llama_batch_ext * batch = llama_batch_ext_init_from_text(prompt_tokens.data(), prompt_tokens.size(), 0, 0, true); - llama_batch_ext_set_output_last(batch); // main loop