mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-16 07:38:28 +00:00
rm redundant llama_batch_ext_set_output_last
This commit is contained in:
@ -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<llama_token> & 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;
|
||||
|
@ -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;
|
||||
}
|
||||
|
@ -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;
|
||||
|
@ -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
|
||||
|
||||
|
Reference in New Issue
Block a user