MCPcopy Create free account
hub / github.com/Tiiny-AI/PowerInfer / llama_model_offload_ffn_split

Function llama_model_offload_ffn_split

llama.cpp:10130–10134  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

10128}
10129
10130size_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
10136int llama_get_kv_cache_token_count(const struct llama_context * ctx) {
10137 return ctx->kv_self.head;

Callers 1

llm_load_gpu_splitFunction · 0.85

Calls 1

offload_ffn_splitMethod · 0.80

Tested by

no test coverage detected