post-train: M2b — batched KV-cache decode (G-way, token-identical)

The rollout long-pole fix deferred from M2a: decode the G samples of one prompt
in lockstep (one forward per step over the group → G× fewer kernel launches).

- rope_pos(x, positions[]): RoPE with a per-row absolute position (new forward-
  only kernel) — G rows share one decode position. Gate: == full rope for
  [0..n], == rope_at(P) per row for uniform P (bit-identical).
- generate_cached_batch: BatchKVCache [T, G·num_kv, hd] + batched decode_step.
  decode_attention is already batch-agnostic (bh = G·nh); repeat_kv(nh, batch=G)
  broadcasts per group. No finished-mask / ragged prompts yet (perf-only / next).
- Gate (tests/decode_batch.rs): all G greedy rows token-identical to the single-
  sequence decode (8 query / 2 kv heads → exercises repeat_kv batching).

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

crates/xtrain-tensor/src/tensor.rs

@@ -822,6 +822,40 @@ impl Tensor {
         out
     }
 
+    /// RoPE with a PER-ROW absolute position (batched KV-cache decode, M2b).
+    /// `self`:[tokens,heads,head_dim]; row `t`'s position is `positions[t]` (an
+    /// I32 `[tokens]` tensor). For G-way batched decode all G rows share one decode
+    /// position; for ragged batches each row carries its own. Mirrors `rope_at`'s
+    /// dtype handling; forward only.
+    #[cfg(not(no_cuda))]
+    pub fn rope_pos(&self, positions: &Tensor, theta: f32) -> Self {
+        assert_eq!(self.ndim(), 3, "rope_pos requires [tokens,heads,head_dim]");
+        let (tokens, heads, head_dim) = (self.shape[0], self.shape[1], self.shape[2]);
+        assert_eq!(head_dim % 2, 0, "head_dim must be even");
+        assert_eq!(positions.dtype, DType::I32, "positions must be I32");
+        assert_eq!(positions.numel(), tokens, "one position per token");
+        if self.dtype == DType::BF16 {
+            return self
+                .to_dtype(DType::F32)
+                .rope_pos(positions, theta)
+                .to_dtype(DType::BF16);
+        }
+        let out = Tensor::zeros(&self.shape, DType::F32, self.device());
+        unsafe {
+            xtrain_cuda::ffi::launch_rope_pos_f32(
+                self.data_ptr() as *const f32,
+                positions.data_ptr() as *const i32,
+                out.data_ptr() as *mut f32,
+                tokens as i32,
+                heads as i32,
+                head_dim as i32,
+                theta,
+                std::ptr::null_mut(),
+            );
+        }
+        out
+    }
+
     /// RoPE backward: apply the inverse (transpose) rotation to `dy`. RoPE is an
     /// orthogonal map, so it needs no cached forward values, only `theta`/`period`.
     #[cfg(not(no_cuda))]