DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: sync ggml and remove obsolete conv1d workarounds (#2147)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-17 02:39:51 +08:00
1 parent 2f016e8e30
commit af0fc72c96
4 files changed
+19 -37
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/model/common/ggml_block.hpp
+1 -1
View File
@@ -13,8 +13,8 @@
#include <vector>
#include "core/ggml_extend.h"
#include "core/ggml_runner.h"
#include "core/ggml_extend_backend.h"
#include "core/ggml_runner.h"
#include "model.h"
class GGMLBlock {
src/model/vae/minimax_h3_audio_vae.hpp
+9 -20
View File
@@ -363,33 +363,22 @@ namespace MiniMaxH3 {
auto pre = std::dynamic_pointer_cast<AudioAttentionProjection>(blocks["pre_block"]);
auto mean_proj = std::dynamic_pointer_cast<LTXV::Conv1D>(blocks["mean_proj"]);
// GGML's batched conv1d storage interleaves the stream dimension
// with output channels. Subsequent layers then read stereo samples
// as adjacent feature channels. Run each mono stream independently,
// matching PyTorch's reshape(B*S, 1, samples), and concatenate only
// the completed normalized latents.
const int64_t streams = waveform->ne[2] * waveform->ne[3];
waveform = ggml_reshape_3d(ctx->ggml_ctx,
waveform,
waveform->ne[0],
1,
streams);
ggml_tensor* stereo_z = nullptr;
for (int64_t stream = 0; stream < streams; ++stream) {
auto mono = ggml_ext_slice(ctx->ggml_ctx, waveform, 2, stream, stream + 1);
auto x = encoder->forward(ctx, mono);
x = ggml_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3));
x = pre->forward(ctx, x);
x = ggml_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3));
auto z = mean_proj->forward(ctx, x);
auto x = encoder->forward(ctx, waveform);
x = ggml_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3));
x = pre->forward(ctx, x);
x = ggml_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, x, 1, 0, 2, 3));
auto z = mean_proj->forward(ctx, x);
auto mean = ggml_reshape_4d(ctx->ggml_ctx, params["latents_mean"], 1, kLatentChannels, 1, 1);
auto std = ggml_reshape_4d(ctx->ggml_ctx, params["latents_std"], 1, kLatentChannels, 1, 1);
z = ggml_div(ctx->ggml_ctx, ggml_sub(ctx->ggml_ctx, z, mean), std);
z = ggml_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, z, 0, 2, 1, 3));
stereo_z = stereo_z == nullptr ? z : ggml_concat(ctx->ggml_ctx, stereo_z, z, 1);
}
return stereo_z;
auto mean = ggml_reshape_4d(ctx->ggml_ctx, params["latents_mean"], 1, kLatentChannels, 1, 1);
auto std = ggml_reshape_4d(ctx->ggml_ctx, params["latents_std"], 1, kLatentChannels, 1, 1);
z = ggml_div(ctx->ggml_ctx, ggml_sub(ctx->ggml_ctx, z, mean), std);
return ggml_cont(ctx->ggml_ctx, ggml_permute(ctx->ggml_ctx, z, 0, 2, 1, 3));
}
ggml_tensor* decode(GGMLRunnerContext* ctx, ggml_tensor* latent) {