server: tensor-parallel HTTP engine (--tp N)

tp_engine: rank-0 coordinator owns the scheduler and broadcasts per-token
commands (Register/Prefill/Decode/Free) to worker rank threads; the sampled
token always comes from rank 0, so it's correct for greedy and stochastic
sampling. Serial single-request path (sufficient for the quality benchmark).
--tp N selects it; TP=1 keeps the existing single-GPU Engine unchanged.

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

crates/xserv-server/Cargo.toml

@@ -13,6 +13,7 @@ xserv-tensor = { path = "../xserv-tensor" }
 xserv-kernels = { path = "../xserv-kernels" }
 xserv-model = { path = "../xserv-model" }
 xserv-tokenizer = { path = "../xserv-tokenizer" }
+xserv-distributed = { path = "../xserv-distributed" }
 half.workspace = true
 serde.workspace = true
 serde_json.workspace = true