35 lines
1.3 KiB
C++
35 lines
1.3 KiB
C++
#include "models.h"
|
|
|
|
ggml_cgraph * mtmd_graph_yue2_gen::build() {
|
|
const auto & y = model.yue2;
|
|
|
|
if (gen_process == MTMD_SUBCTX_GEN_PROCESS_LATENT_IN || gen_process == MTMD_SUBCTX_GEN_PROCESS_LATENT_OUT) {
|
|
const bool is_in = gen_process == MTMD_SUBCTX_GEN_PROCESS_LATENT_IN;
|
|
ggml_tensor * w = is_in ? y.inp_w : y.out_w;
|
|
ggml_tensor * b = is_in ? y.inp_b : y.out_b;
|
|
ggml_tensor * cur = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, w->ne[0], n_rows);
|
|
ggml_set_name(cur, "inp_feats");
|
|
ggml_set_input(cur);
|
|
cur = ggml_add(ctx0, build_mm(w, cur), b);
|
|
ggml_set_name(cur, "out_feats");
|
|
ggml_set_output(cur);
|
|
ggml_build_forward_expand(gf, cur);
|
|
return gf;
|
|
}
|
|
|
|
GGML_ASSERT(gen_process == MTMD_SUBCTX_GEN_PROCESS_GEN_WAV);
|
|
|
|
ggml_tensor * inp = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_latent, n_rows);
|
|
ggml_set_name(inp, "inp_feats");
|
|
ggml_set_input(inp);
|
|
|
|
ggml_tensor * x = ggml_cont(ctx0, ggml_transpose(ctx0, inp)); // [T, n_latent]
|
|
x = build_snake_vae(x, model.snake_vae); // [T, n_channels]
|
|
|
|
x = ggml_cont(ctx0, ggml_transpose(ctx0, x)); // interleaved
|
|
ggml_set_name(x, "out_audio");
|
|
ggml_set_output(x);
|
|
ggml_build_forward_expand(gf, x);
|
|
return gf;
|
|
}
|