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/stream.rs

@@ -31,3 +31,39 @@ impl Drop for CudaStream {
 
 // Can move across threads, but not shared without synchronization
 unsafe impl Send for CudaStream {}
+
+// --- Thread-local launch stream -------------------------------------------
+//
+// Every kernel wrapper in xserv-kernels launches on `current_stream_raw()`,
+// which defaults to the legacy null stream (the historical behavior). CUDA
+// graph capture requires work to be issued on an explicit stream, so capture
+// code installs its stream here for the duration of the captured region via
+// `push_stream` / `StreamGuard`.
+
+use std::cell::Cell;
+
+thread_local! {
+    static CURRENT_STREAM: Cell<ffi::CudaStream> = const { Cell::new(std::ptr::null_mut()) };
+}
+
+/// The stream kernel launches on this thread should use (null = legacy default).
+pub fn current_stream_raw() -> ffi::CudaStream {
+    CURRENT_STREAM.with(|c| c.get())
+}
+
+/// RAII guard that installs a launch stream for the current thread and
+/// restores the previous one on drop.
+pub struct StreamGuard {
+    prev: ffi::CudaStream,
+}
+
+pub fn push_stream(stream: &CudaStream) -> StreamGuard {
+    let prev = CURRENT_STREAM.with(|c| c.replace(stream.as_raw()));
+    StreamGuard { prev }
+}
+
+impl Drop for StreamGuard {
+    fn drop(&mut self) {
+        CURRENT_STREAM.with(|c| c.set(self.prev));
+    }
+}