tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +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

4
examples/run/run.cpp
View File

@ -946,7 +946,7 @@ static int generate(LlamaData & llama_data, const std::string & prompt, std::str
}
// prepare a batch for the prompt
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), tokens.size(), 0, 0));
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tokens.data(), tokens.size(), 0, 0, true));
llama_token new_token_id;
while (true) {
check_context_size(llama_data.context, batch);
@ -969,7 +969,7 @@ static int generate(LlamaData & llama_data, const std::string & prompt, std::str
print_word_and_concatenate_to_response(piece, response);
// prepare the next batch with the sampled token
batch.reset(llama_batch_ext_init_from_text(&new_token_id, 1, 0, 0));
batch.reset(llama_batch_ext_init_from_text(&new_token_id, 1, 0, 0, true));
}
printf(LOG_COL_DEFAULT);