cuda: infrastructure for whole-step CUDA graph capture

- Thread-local launch stream (xserv_cuda::stream): every kernel
  wrapper, cublasSetStream, and NCCL collective now launches on
  current_stream_raw() — the legacy null stream by default (behavior
  unchanged), or the capture stream installed via push_stream during
  graph capture. Capture is impossible on the legacy stream.
- Allocator retain mode: blocks freed inside a retain window are
  quarantined (RetainedBlocks) instead of pooled, so an instantiated
  graph keeps exclusive ownership of every intermediate buffer it
  references across replays.
- Capture mode GLOBAL -> THREAD_LOCAL: concurrent TP rank threads
  must not poison each other's captures with their own cudaMallocs.
- embedding_device_ids / rope_inplace_device_pos: variants reading
  token ids / positions from persistent device buffers, replacing the
  per-call host upload that a captured region cannot contain.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

crates/xserv-cuda/src/allocator.rs

@@ -111,6 +111,22 @@ pub fn cached_trim() {
 /// Called from `GpuBuffer::Drop` for pooled buffers. Takes raw pointer
 /// and size to avoid re-triggering Drop.
 pub fn return_to_pool(ptr: *mut u8, len: usize) {
+    // During CUDA graph capture, buffers freed by the captured code are
+    // quarantined instead of pooled: the instantiated graph references their
+    // addresses on every replay, so they must never be handed to another
+    // consumer for as long as the graph lives.
+    let quarantined = RETAINED.with(|cell| {
+        let mut r = cell.borrow_mut();
+        if let Some(list) = r.as_mut() {
+            list.push((ptr, len));
+            true
+        } else {
+            false
+        }
+    });
+    if quarantined {
+        return;
+    }
     ALLOCATOR.with(|cell| {
         let mut alloc = cell.borrow_mut();
         let bucket = bucket_size(len);
@@ -119,6 +135,41 @@ pub fn return_to_pool(ptr: *mut u8, len: usize) {
     });
 }
 
+thread_local! {
+    static RETAINED: RefCell<Option<Vec<(*mut u8, usize)>>> = const { RefCell::new(None) };
+}
+
+/// Buffers freed while a retain window was active. Holding this keeps their
+/// memory out of the pool; dropping it returns the blocks (on the owning
+/// thread) for reuse.
+pub struct RetainedBlocks(Vec<(*mut u8, usize)>);
+
+impl Drop for RetainedBlocks {
+    fn drop(&mut self) {
+        for (ptr, len) in self.0.drain(..) {
+            return_to_pool(ptr, len);
+        }
+    }
+}
+
+/// Start quarantining buffers freed on this thread (see `return_to_pool`).
+/// Must be paired with `end_retain` on the same thread; nesting unsupported.
+pub fn begin_retain() {
+    RETAINED.with(|cell| {
+        let mut r = cell.borrow_mut();
+        assert!(r.is_none(), "begin_retain: retain window already active");
+        *r = Some(Vec::new());
+    });
+}
+
+/// Stop quarantining and hand the quarantined blocks to the caller.
+pub fn end_retain() -> RetainedBlocks {
+    RETAINED.with(|cell| {
+        let list = cell.borrow_mut().take().expect("end_retain without begin_retain");
+        RetainedBlocks(list)
+    })
+}
+
 /// Round up to next power-of-2, minimum 512 bytes.
 fn bucket_size(size: usize) -> usize {
     let min = 512;