ops: embedding/reshape/transpose/split-merge-heads fwd+bwd

Phase T5 structural ops on top of the T4 set, needed to assemble the
tiny transformer:
- embedding: gather rows by I32 ids (CUDA kernel) / scatter-add backward
  (atomic, so repeated ids accumulate). csrc/ops/model.cu + ffi.
- reshape: contiguous metadata-only view (Tensor::reshape), no kernel.
- transpose_3d01: [a,b,c]->[b,a,c] for the multi-head layout (kernel).
- autograd nodes: embedding/reshape/transpose_3d01/transpose_2d, plus
  split_heads (->Vec<Var>) / merge_heads for per-head attention.
- tape: Var::zero_grad + set_value so a hand-written GD step can update
  params and clear grads between steps.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

crates/xtrain-cuda/src/ffi.rs

@@ -177,6 +177,41 @@ unsafe extern "C" {
     );
 }
 
+// Structural ops for the tiny transformer (csrc/ops/model.cu): token embedding
+// (gather fwd / scatter-add bwd) and a 3D axis-(0,1) transpose for the multi-head
+// attention layout. F32 values, I32 ids, row-major contiguous.
+#[cfg(not(no_cuda))]
+unsafe extern "C" {
+    // Embedding: out[s,:] = table[ids[s], :]. table:[vocab,dim], ids:[seq] (I32).
+    pub fn launch_embedding_fwd_f32(
+        table: *const f32,
+        ids: *const i32,
+        out: *mut f32,
+        seq: i32,
+        dim: i32,
+        s: CudaStream,
+    );
+    // Scatter-add: dtable[ids[s],:] += dout[s,:] (dtable pre-zeroed; atomic).
+    pub fn launch_embedding_bwd_f32(
+        dout: *const f32,
+        ids: *const i32,
+        dtable: *mut f32,
+        seq: i32,
+        dim: i32,
+        s: CudaStream,
+    );
+
+    // 3D axis-(0,1) transpose: in:[a,b,c] -> out:[b,a,c]. out[j,i,k]=in[i,j,k].
+    pub fn launch_transpose_3d01_f32(
+        input: *const f32,
+        out: *mut f32,
+        a: i32,
+        b: i32,
+        c: i32,
+        s: CudaStream,
+    );
+}
+
 // cuBLAS — used ONLY as a correctness reference for the hand-written GEMM in
 // tests. Declared (and linked, see build.rs) only when CUDA is compiled in.
 #[cfg(not(no_cuda))]