tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

return output ID from llama_batch_ext_add/set

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 17:47:07 +01:00
parent 86973cb14a
commit 4aabf4e8f4
5 changed files with 31 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/batched/batched.cpp
View File

@ -131,7 +131,7 @@ int main(int argc, char ** argv) {
}
// llama_decode will output logits only for the last token of the prompt
llama_batch_ext_set_logits_last(batch);
llama_batch_ext_set_output_last(batch);
if (llama_decode_ext(ctx, batch) != 0) {
LOG_ERR("%s: llama_decode() failed\n", __func__);