model: try to improve Qwen3 Next (#18683)

* qwen3next: simplify qkvz projection

* use ggml_swiglu_split

* revert swiglu_split, but remove redundant repeat()

* fix missing reshape

* rm 2 redundant transposes

* move mul_mat(k,q) to outside of chunking

* rm redundant cont

* improve g_cs_chunk

* add comments about no cont

* use std::pair instead of ggml_concat

* vectorize key_gdiff calculation

* rm unused tensor

* avoid ggml_concat inside loop

* bring back ggml_concat as it may not work on other backend

* nits

src/models/models.h

@@ -466,7 +466,8 @@ private:
                 ggml_tensor * cur,
                         int   il);
 
-    ggml_tensor * build_delta_net_chunking(
+    // returns pair of output and new state
+    std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_chunking(
                 ggml_tensor * q,
                 ggml_tensor * k,
                 ggml_tensor * v,
@@ -478,7 +479,8 @@ private:
                 ggml_tensor * diag_mask,
                         int   il);
 
-    ggml_tensor * build_delta_net_autoregressive(
+    // returns pair of output and new state
+    std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_autoregressive(
                 ggml_tensor * q,
                 ggml_tensor * k,
                 ggml_tensor * v,
@@ -493,6 +495,11 @@ private:
                 ggml_tensor * gate,
                         int   layer);
 
+    // returns pair of qkv, z
+    std::pair<ggml_tensor *, ggml_tensor *> build_qkvz(
+                ggml_tensor * input,
+                        int   il);
+
     const llama_model & model;
 };