Function ggml_rope_impl

ggml.c:5029–5075

// ggml_rope

static struct ggml_tensor * ggml_rope_impl(
        struct ggml_context * ctx,
        struct ggml_tensor  * a,
        struct ggml_tensor  * b,
        int                   n_dims,
        int                   mode,
        int                   n_ctx,
        int                   n_orig_ctx,
        float                 freq_base,
        float                 freq_scale,
        float                 ext_factor,
        float                 attn_factor,
        float                 beta_fast,
        float                 beta_slow,
        float                 xpos_base,
        bool                  xpos_down,
        bool                  inplace) {
    GGML_ASSERT(ggml_is_vector(b));
    GGML_ASSERT(b->type == GGML_TYPE_I32);
    GGML_ASSERT(a->ne[2] == b->ne[0]);

    bool is_node = false;

    if (a->grad) {
        is_node = true;
    }

    struct ggml_tensor * result = inplace ? ggml_view_tensor(ctx, a) : ggml_dup_tensor(ctx, a);

    int32_t params[13] = { /*n_past*/ 0, n_dims, mode, n_ctx, n_orig_ctx };
    memcpy(params +  5, &freq_base,    sizeof(float));
    memcpy(params +  6, &freq_scale,   sizeof(float));
    memcpy(params +  7, &ext_factor,   sizeof(float));
    memcpy(params +  8, &attn_factor,  sizeof(float));
    memcpy(params +  9, &beta_fast,    sizeof(float));
    memcpy(params + 10, &beta_slow,    sizeof(float));
    memcpy(params + 11, &xpos_base,    sizeof(float));
    memcpy(params + 12, &xpos_down,    sizeof(bool));
    ggml_set_op_params(result, params, sizeof(params));

    result->op   = GGML_OP_ROPE;
    result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
    result->src[0] = a;
    result->src[1] = b;

    return result;
}

struct ggml_tensor * ggml_rope(
        struct ggml_context * ctx,