CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

mtmd-helper : bug fix to token batching in mtmd (#13650)

Browse Source 
* Update mtmd-helper.cpp

* Update tools/mtmd/mtmd-helper.cpp

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

---------

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
l3utterfly
2025-05-21 00:55:30 +08:00
committed by GitHub
parent be0239693c
commit b7a17463ec
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tools/mtmd/mtmd-helper.cpp
View File

@@ -231,12 +231,14 @@ int32_t mtmd_helper_eval_chunk_single(mtmd_context * ctx,
while (i < n_tokens) { // split into batches
text_batch.n_tokens = 0; // clear the batch
for (; i < n_tokens && text_batch.n_tokens < n_batch; i++) {
int32_t j = text_batch.n_tokens;
text_batch.token [j] = tokens[i];
text_batch.pos [j] = n_past++;
text_batch.n_seq_id[j] = 1;
text_batch.seq_id [j][0] = seq_id;
text_batch.logits [j] = false;
text_batch.n_tokens++;
text_batch.token [i] = tokens[i];
text_batch.pos [i] = n_past++;
text_batch.n_seq_id[i] = 1;
text_batch.seq_id [i][0] = seq_id;
text_batch.logits [i] = false;
}
bool is_last_token = (i == n_tokens);
if (logits_last && is_last_token) {