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

Function llama_use_sparse_inference

llama.cpp:10052–10054  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

10050}
10051
10052bool llama_use_sparse_inference(const struct llama_model * model) {
10053 return model->sparse_deriv == GGML_SPARSE_INFERENCE;
10054}
10055
10056int llama_n_vocab(const struct llama_model * model) {
10057 return model->vocab.id_to_token.size();

Callers 4

llama_model_loadFunction · 0.85
build_llama_variantsMethod · 0.85
build_optMethod · 0.85
build_falconMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected