| 10128 | } |
| 10129 | |
| 10130 | size_t llama_model_offload_ffn_split(struct llama_model * model) { |
| 10131 | llama_augmentation_model_loader * aug_ml = new llama_augmentation_model_loader(model); |
| 10132 | size_t offloaded_bytes = aug_ml->offload_ffn_split(model); |
| 10133 | return offloaded_bytes; |
| 10134 | } |
| 10135 | |
| 10136 | int llama_get_kv_cache_token_count(const struct llama_context * ctx) { |
| 10137 | return ctx->kv_self.head; |
no test coverage detected