gqa: real grouped-query attention (repeat_kv op + both SDPA paths + wiring + tests)

- repeat_kv CUDA kernel: fwd head-block gather, bwd DETERMINISTIC group-sum (each
  kv head sums its group of query-head grads; no atomics) + Tensor/ops node.
- Config gains num_kv_heads (default = n_heads → MHA); wk/wv project to kv_dim;
  attention() repeat_kv-broadcasts K/V to nh heads before the UNCHANGED composed
  & flash SDPA → GQA on both paths. group=1 is identity → MHA bit-identical.
- --kv-heads flag on train/train_ddp/export_safetensors/greedy_sample; export
  writes real num_key_value_heads (xserv repeat_kv grouping aligned).
- Tests: repeat_kv grad-check (group>1 grad-sum + group=1 identity); model gqa.rs
  (GQA flash==composed fp32/bf16, group=1 bit-identical to MHA, kv-proj shape);
  parity_dump+parity.py GQA path (repeat_interleave) via XTRAIN_PARITY_KV_HEADS.

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

crates/xtrain-cuda/build.rs

@@ -37,6 +37,7 @@ fn main() {
         .file("../../csrc/ops/optim.cu")
         .file("../../csrc/ops/attention.cu")
         .file("../../csrc/ops/flash_attention.cu")
+        .file("../../csrc/ops/repeat_kv.cu")
         .file("../../csrc/ops/cast.cu")
         .file("../../csrc/ops/dropout.cu")
         .compile("xtrain_cuda_kernels");

crates/xtrain-cuda/src/ffi.rs

@@ -296,6 +296,37 @@ unsafe extern "C" {
     );
 }
 
+// GQA repeat_kv head broadcast (csrc/ops/repeat_kv.cu, Phase T15). Expands a K/V
+// tensor from [batch·num_kv, S, hd] to the full [batch·nh, S, hd] so the SDPA
+// (composed or flash, both untouched) sees a full set of heads. Forward gathers
+// (out head qh ← kv head qh/group, group = nh/num_kv); backward sums the `group`
+// query heads sharing each kv head (deterministic, no atomics). All F32.
+#[cfg(not(no_cuda))]
+unsafe extern "C" {
+    // Forward: out[b·nh+qh] = in[b·num_kv + qh/group], per [S,hd] head block.
+    pub fn launch_repeat_kv_fwd_f32(
+        input: *const f32,
+        out: *mut f32,
+        batch: i32,
+        nh: i32,
+        num_kv: i32,
+        seq: i32,
+        hd: i32,
+        s: CudaStream,
+    );
+    // Backward: din[b·num_kv+kvh] = Σ_{r<group} dout[b·nh + kvh·group + r].
+    pub fn launch_repeat_kv_bwd_f32(
+        dout: *const f32,
+        din: *mut f32,
+        batch: i32,
+        nh: i32,
+        num_kv: i32,
+        seq: i32,
+        hd: i32,
+        s: CudaStream,
+    );
+}
+
 // GPU-side optimizer kernels (csrc/ops/optim.cu): AdamW step (m/v on device) and
 // the global grad-norm reduction + in-place rescale (Phase T7).
 #[cfg(not(no_cuda))]