Method n_gqa

subprojects/llama.cpp/src/llama-hparams.cpp:54–63

}

uint32_t llama_hparams::n_gqa(uint32_t il) const {
    const uint32_t n_head    = this->n_head(il);
    const uint32_t n_head_kv = this->n_head_kv(il);

    if (n_head_kv == 0) {
        return 0;
    }

    return n_head/n_head_kv;
}

uint32_t llama_hparams::n_embd_inp() const {
    uint32_t n_embd_inp = n_embd;