perf: GPU AdamW + grad-norm

Eliminate the per-step GPU↔host roundtrip of every parameter/gradient.

- optim.cu: adamw_step (m/v on device, in-place param update), sumsq_accum
  (block-reduced global grad sum-of-squares), scale_inplace.
- GpuAdamW: device m/v state per param; step launches the kernel reading
  each param's .grad() and rewriting the param buffer in place — no host
  roundtrip. Host AdamW kept as the torch-parity reference.
- clip_grad_norm_gpu: device sum-of-squares reduction (only the scalar norm
  comes back), in-place rescale of grads by pre_scale·clip_factor.
- train_loop: use GpuAdamW + clip_grad_norm_gpu.
- test: GPU AdamW vs host reference parity (max abs err < 1e-6).

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

crates/xtrain-cuda/build.rs

@@ -34,6 +34,7 @@ fn main() {
         .file("../../csrc/ops/gemm.cu")
         .file("../../csrc/ops/nn.cu")
         .file("../../csrc/ops/model.cu")
+        .file("../../csrc/ops/optim.cu")
         .compile("xtrain_cuda_kernels");
 }
 

crates/xtrain-cuda/src/ffi.rs

@@ -212,6 +212,34 @@ unsafe extern "C" {
     );
 }
 
+// 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))]
+unsafe extern "C" {
+    // One in-place AdamW step over a parameter tensor of `n` elements. `bc1`/`bc2`
+    // are the bias-correction denominators 1-beta^t.
+    #[allow(clippy::too_many_arguments)]
+    pub fn launch_adamw_step_f32(
+        p: *mut f32,
+        g: *const f32,
+        m: *mut f32,
+        v: *mut f32,
+        lr: f32,
+        b1: f32,
+        b2: f32,
+        eps: f32,
+        wd: f32,
+        bc1: f32,
+        bc2: f32,
+        n: i32,
+        s: CudaStream,
+    );
+    // acc += sum_i g[i]^2 (acc is one f32 on device, pre-zeroed). atomicAdd.
+    pub fn launch_sumsq_accum_f32(g: *const f32, acc: *mut f32, n: i32, s: CudaStream);
+    // In-place scalar scale: x[i] *= factor.
+    pub fn launch_scale_inplace_f32(x: *mut f32, factor: f32, n: i32, s: CudaStream);
+}
+
 // cuBLAS — the production GEMM backend (Phase T7) and the correctness oracle the
 // T3 GEMM tests still compare against. Declared (and linked, see build.rs) only
 // when CUDA is compiled in.