kanshan/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-08 20:20:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

batched : fix n_seq_id

Browse Source
This commit is contained in:
Georgi Gerganov
2023-10-16 00:03:41 +03:00
parent 7e48e21b1f
commit 0d96efabb5
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/batched/batched.cpp
+5 -4
View File
@@ -106,10 +106,11 @@ int main(int argc, char ** argv) {
batch.n_tokens = tokens_list.size();
for (int32_t i = 0; i < batch.n_tokens; i++) {
batch.token[i] = tokens_list[i];
batch.pos[i] = i;
batch.seq_id[i] = 0;
batch.logits[i] = false;
batch.token[i] = tokens_list[i];
batch.pos[i] = i;
batch.n_seq_id[i] = 1;
batch.seq_id[i][0] = 0;
batch.logits[i] = false;
}
// llama_decode will output logits only for the last token of the prompt