tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix llama_batch_ext_init_from_text

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 23:09:27 +01:00
parent 65f0184517
commit c3dd79007b
18 changed files with 40 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/main/main.cpp
View File

@ -548,7 +548,7 @@ int main(int argc, char ** argv) {
int enc_input_size = embd_inp.size();
llama_token * enc_input_buf = embd_inp.data();
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(enc_input_buf, enc_input_size, 0, 0));
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(enc_input_buf, enc_input_size, 0, 0, true));
if (llama_decode_ext(ctx, batch.get())) {
LOG_ERR("%s : failed to eval\n", __func__);
return 1;
@ -669,7 +669,8 @@ int main(int argc, char ** argv) {
LOG_DBG("eval: %s\n", string_from(ctx, embd).c_str());
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(&embd[i], n_eval, 0, 0));
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(&embd[i], n_eval, n_past, 0, true));
llama_batch_ext_set_output_last(batch.get());
if (llama_decode_ext(ctx, batch.get())) {
LOG_ERR("%s : failed to eval\n", __func__);
return 1;