metal : optimize Metal Tensor API usage for GGML_OP_MUL_MAT (#20962)

* Optimize Metal Tensor API usage for matmul2d

Separates the Metal Tensor API (matmul2d) path in kernel_mul_mm into its own standalone kernel, gated by GGML_METAL_HAS_TENSOR.

The legacy simdgroup_matrix kernel is preserved under #else.

Previously both paths were interleaved via #ifdef blocks within a single kernel, forcing the tensor path to share the legacy kernel's data layout and threadgroup memory scheme. Splitting the kernel enabled memory and dispatch optimizations that weren't possible when the two paths shared code structure.

* cont : cleanup

* cont : cleanup

* cont : cleanup

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

ggml/src/ggml-metal/ggml-metal-impl.h

@@ -1,6 +1,19 @@
 #ifndef GGML_METAL_IMPL
 #define GGML_METAL_IMPL
 
+// kernel parameters for mat-mat threadgroups
+//
+// TODO: become function constants
+
+#define SZ_SIMDGROUP 16
+#define N_MM_NK 2
+#define N_MM_NK_TOTAL (SZ_SIMDGROUP * N_MM_NK)
+
+#define N_MM_BLOCK_X 4
+#define N_MM_BLOCK_Y 2
+#define N_MM_SIMD_GROUP_X 2
+#define N_MM_SIMD_GROUP_Y 2
+
 // kernel parameters for mat-vec threadgroups
 //
 // N_R0: number of src0 rows to process per simdgroup