post-train: M4 — clipped_pg_loss + scale_rows (GRPO policy-gradient op)

The GRPO (M4) token-level loss op + the one primitive it needs:

- scale_rows(x[r,c], s[r]): per-row scale (new ~5-line CUDA kernel). The
  clipped-PG backward scales each completion token's row of (probs − onehot) by
  its own per-token coefficient, which cross_entropy_backward's single scalar
  scale can't express.
- clipped_pg_loss(logits, target, logp_old, logp_ref, A, eps, beta): per-token
  ρ_t = exp(logπθ_t − logp_old_t), L = −mean min(ρA, clip(ρ,1±ε)A) + β·mean KL
  (k3 estimator), masked to completion tokens. Backward reuses the CE machinery
  (probs − onehot) + scale_rows. Gates: grad-check the active PG path + the A=0
  (KL-only) path; degenerate value checks ε→∞ ⇒ vanilla PG, β=0 ⇒ no KL.

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

crates/xtrain-tensor/src/tensor.rs

@@ -941,6 +941,31 @@ impl Tensor {
         dx
     }
 
+    /// Per-row scale: `out[r,c] = self[r,c] * s[r]`. `self`:[rows,cols] F32,
+    /// `s`:[rows] F32. Used by the GRPO (M4) policy-gradient backward, where each
+    /// completion token's row of `(probs − onehot)` is scaled by its own per-token
+    /// coefficient (the per-token clipped-PG + KL gradient). Forward-only.
+    #[cfg(not(no_cuda))]
+    pub fn scale_rows(&self, s: &Tensor) -> Self {
+        assert_eq!(self.ndim(), 2, "scale_rows requires a 2D tensor");
+        assert_eq!(self.dtype, DType::F32, "scale_rows is F32");
+        assert_eq!(s.dtype, DType::F32, "scale vector is F32");
+        let (rows, cols) = (self.shape[0], self.shape[1]);
+        assert_eq!(s.numel(), rows, "scale vector must have one entry per row");
+        let out = Tensor::zeros(&self.shape, DType::F32, self.device());
+        unsafe {
+            xtrain_cuda::ffi::launch_scale_rows_f32(
+                self.data_ptr() as *const f32,
+                s.data_ptr() as *const f32,
+                out.data_ptr() as *mut f32,
+                rows as i32,
+                cols as i32,
+                std::ptr::null_mut(),
+            );
+        }
+        out
+    }
+
     // --- Structural / model ops (the T5 kernels) ---
 
     /// Reshape to `new_shape` (must keep `numel`). Pure metadata change on a