speculative: copy_kv_position primitive for tree drafting KV remap

SGLang-style "write-all, copy-move on acceptance" approach: after tree
verification, physically copy an accepted sibling's K/V from its
physical cache slot to the canonical sequential position.

New CUDA kernel: copy_kv_position_kernel in reshape_and_cache.cu.
For one token (src_pos → dst_pos), copies head_dim × num_kv_heads BF16
elements in both K and V pools. Grid = num_kv_heads, block = head_dim.
Cost for one token across 36 layers: ~5.3 MB D2D copy @ 900 GB/s = <6μs.

Rust FFI: copy_kv_position(k_pool, v_pool, block_ids, src_pos, dst_pos,
num_kv_heads, head_dim, block_size, stream).

PagedKVCache method: copy_kv_position(slot, src_pos, dst_pos) — uploads
block_ids for the sequence, calls the kernel per layer. This is the
primitive needed by tree drafting: when a non-primary sibling at cache
position P+2 is accepted as the "true" token for target position P+1,
call copy_kv_position(slot, P+2, P+1) then truncate to P+2.

Next: wire into bench-eagle3 tree drafting loop with top-2 siblings.

crates/xserv-kernels/src/attention.rs

@@ -145,6 +145,17 @@ unsafe extern "C" {
         max_blocks_per_seq: i32,
         stream: *mut c_void,
     );
+    fn launch_copy_kv_position(
+        k_pool: *mut c_void,
+        v_pool: *mut c_void,
+        block_ids: *const i32,
+        src_pos: i32,
+        dst_pos: i32,
+        num_kv_heads: i32,
+        head_dim: i32,
+        block_size: i32,
+        stream: *mut c_void,
+    );
 }
 
 /// Scatter `[num_kv_heads, num_tokens, head_dim]` BF16 K/V into a paged
@@ -231,6 +242,36 @@ pub unsafe fn reshape_and_cache_batched_bf16(
     }
 }
 
+/// Copy one token's K/V from `src_pos` to `dst_pos` within the same sequence's
+/// paged cache (one layer). Used by tree speculative decoding to remap
+/// accepted sibling K/V to canonical sequential positions after acceptance.
+///
+/// # Safety
+/// Pool and block_ids pointers must be valid GPU pointers for the given layer.
+pub unsafe fn copy_kv_position(
+    k_pool_ptr: *mut c_void,
+    v_pool_ptr: *mut c_void,
+    block_ids_gpu: *const i32,
+    src_pos: usize,
+    dst_pos: usize,
+    num_kv_heads: usize,
+    head_dim: usize,
+    block_size: usize,
+    stream: *mut c_void,
+) {
+    launch_copy_kv_position(
+        k_pool_ptr,
+        v_pool_ptr,
+        block_ids_gpu,
+        src_pos as i32,
+        dst_pos as i32,
+        num_kv_heads as i32,
+        head_dim as i32,
+        block_size as i32,
+        stream,
+    );
+}
+
 fn apply_causal_mask(scores: &Tensor, offset: usize) {
     let ndim = scores.ndim();
     let rows = scores.shape()[ndim - 2];