| 1451 | } |
| 1452 | |
| 1453 | void common_batch_add( |
| 1454 | struct llama_batch & batch, |
| 1455 | llama_token id, |
| 1456 | llama_pos pos, |
| 1457 | const std::vector<llama_seq_id> & seq_ids, |
| 1458 | bool logits) { |
| 1459 | GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded"); |
| 1460 | |
| 1461 | batch.token [batch.n_tokens] = id; |
| 1462 | batch.pos [batch.n_tokens] = pos; |
| 1463 | batch.n_seq_id[batch.n_tokens] = seq_ids.size(); |
| 1464 | for (size_t i = 0; i < seq_ids.size(); ++i) { |
| 1465 | batch.seq_id[batch.n_tokens][i] = seq_ids[i]; |
| 1466 | } |
| 1467 | batch.logits [batch.n_tokens] = logits; |
| 1468 | |
| 1469 | batch.n_tokens++; |
| 1470 | } |
| 1471 | |
| 1472 | // |
| 1473 | // Token utils |