| 2685 | } |
| 2686 | |
| 2687 | int32_t llama_decode( |
| 2688 | llama_context * ctx, |
| 2689 | llama_batch batch) { |
| 2690 | const int ret = ctx->decode(batch); |
| 2691 | if (ret != 0 && ret != 1) { |
| 2692 | LLAMA_LOG_ERROR("%s: failed to decode, ret = %d\n", __func__, ret); |
| 2693 | } |
| 2694 | |
| 2695 | return ret; |
| 2696 | } |
| 2697 | |
| 2698 | // |
| 2699 | // perf |