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

src/core/ggml_extend.cpp

@@ -344,22 +344,15 @@ ggml_tensor* ggml_ext_pad(ggml_context* ctx,
 }
 
 static ggml_tensor* conv_1d(ggml_context* ctx, ggml_tensor* x, ggml_tensor* w, int s0, int p0, int d0, bool force_prec_f32) {
-    ggml_tensor* result;
+    if (!force_prec_f32) {
-    if (force_prec_f32) {
+        return ggml_conv_1d(ctx, w, x, s0, p0, d0);
+    }
     ggml_tensor* patches = ggml_im2col(ctx, w, x, s0, 0, p0, 0, d0, 0, false, GGML_TYPE_F32);
-        result               = ggml_mul_mat(ctx,
+    ggml_tensor* result  = ggml_mul_mat(ctx,
                                         ggml_reshape_2d(ctx, patches, patches->ne[0], patches->ne[2] * patches->ne[1]),
                                         ggml_reshape_2d(ctx, w, w->ne[0] * w->ne[1], w->ne[2]));
-        result               = ggml_reshape_3d(ctx, result, patches->ne[1], w->ne[2], patches->ne[2]);
+    result               = ggml_reshape_3d(ctx, result, patches->ne[1], patches->ne[2], w->ne[2]);
-    } else {
+    return ggml_cont(ctx, ggml_permute(ctx, result, 0, 2, 1, 3));
-        result = ggml_conv_1d(ctx, w, x, s0, p0, d0);
-    }
-    if (x->ne[2] > 1) {
-        // mul_mat packs positions and batches before output channels: [OL, N, OC].
-        result = ggml_reshape_3d(ctx, result, result->ne[0], x->ne[2], w->ne[2]);
-        result = ggml_cont(ctx, ggml_permute(ctx, result, 0, 2, 1, 3));
-    }
-    return result;
 }
 
 ggml_tensor* ggml_ext_conv_1d(ggml_context* ctx,

src/model/common/ggml_block.hpp

@@ -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

@@ -363,21 +363,13 @@ 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;
+            auto x                = encoder->forward(ctx, waveform);
-            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));
@@ -386,10 +378,7 @@ namespace MiniMaxH3 {
             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));
+            return 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;
         }
 
         ggml_tensor* decode(GGMLRunnerContext* ctx, ggml_tensor* latent) {