Method llm_build_plm

subprojects/llama.cpp/src/models/plm.cpp:3–169

#include "models.h"

llm_build_plm::llm_build_plm(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    const float kq_scale = 1.0f/sqrtf(float(hparams.n_embd_head_k));

    const uint32_t n_embd_head_qk_rope = hparams.n_rot;
    const uint32_t n_embd_head_qk_nope = hparams.n_embd_head_k - hparams.n_rot;

    const uint32_t kv_lora_rank = hparams.n_lora_kv;

    ggml_tensor * cur;
    ggml_tensor * inpL;

    // {n_embd, n_tokens}
    inpL = build_inp_embd(model.tok_embd);

    // inp_pos - contains the positions
    ggml_tensor * inp_pos = build_inp_pos();

    auto * inp_attn = build_attn_inp_kv();

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        ggml_tensor * inpSA = inpL;

        // norm
        cur = build_norm(inpL,
                model.layers[il].attn_norm, NULL,
                LLM_NORM_RMS, il);
        cb(cur, "attn_norm", il);

        // self_attention
        {
            ggml_tensor * q = NULL;
            q = ggml_mul_mat(ctx0, model.layers[il].wq, cur);
            cb(q, "q", il);

            // split into {n_head * n_embd_head_qk_nope, n_tokens}
            ggml_tensor * q_nope = ggml_view_3d(ctx0, q, n_embd_head_qk_nope, n_head, n_tokens,
                    ggml_row_size(q->type, hparams.n_embd_head_k),
                    ggml_row_size(q->type, hparams.n_embd_head_k * n_head),
                    0);
            cb(q_nope, "q_nope", il);

            // and {n_head * n_embd_head_qk_rope, n_tokens}
            ggml_tensor * q_pe = ggml_view_3d(ctx0, q, n_embd_head_qk_rope, n_head, n_tokens,
                    ggml_row_size(q->type, hparams.n_embd_head_k),
                    ggml_row_size(q->type, hparams.n_embd_head_k * n_head),
                    ggml_row_size(q->type, n_embd_head_qk_nope));
            cb(q_pe, "q_pe", il);

            // {n_embd, kv_lora_rank + n_embd_head_qk_rope} * {n_embd, n_tokens} -> {kv_lora_rank + n_embd_head_qk_rope, n_tokens}
            ggml_tensor * kv_pe_compresseed = ggml_mul_mat(ctx0, model.layers[il].wkv_a_mqa, cur);
            cb(kv_pe_compresseed, "kv_pe_compresseed", il);

            // split into {kv_lora_rank, n_tokens}
            ggml_tensor * kv_compressed = ggml_view_2d(ctx0, kv_pe_compresseed, kv_lora_rank, n_tokens,
                    kv_pe_compresseed->nb[1],
                    0);