distributed: NCCL tensor-parallel primitives (TpContext + AllReduce)

New xserv-distributed crate: hand-written NCCL FFI, TpContext (one rank per
thread, bound to one GPU), and in-place BF16 AllReduce on the null stream so
it orders naturally with the model's kernels. 2-GPU AllReduce test included.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Cargo.toml

@@ -7,6 +7,7 @@ members = [
     "crates/xserv-model",
     "crates/xserv-tokenizer",
     "crates/xserv-server",
+    "crates/xserv-distributed",
 ]
 
 [workspace.package]