| 3488 | } |
| 3489 | |
| 3490 | int32_t llama_decode( |
| 3491 | llama_context * ctx, |
| 3492 | llama_batch batch) { |
| 3493 | const int ret = ctx->decode(batch); |
| 3494 | if (ret != 0 && ret != 1) { |
| 3495 | LLAMA_LOG_ERROR("%s: failed to decode, ret = %d\n", __func__, ret); |
| 3496 | } |
| 3497 | |
| 3498 | return ret; |
| 3499 | } |
| 3500 | |
| 3501 | // |
| 3502 | // perf |