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/src/main.rs

@@ -1,5 +1,6 @@
 mod api;
 mod engine;
+mod tp_engine;
 
 use axum::{routing::{get, post}, Extension, Router};
 use std::path::PathBuf;
@@ -18,7 +19,7 @@ pub struct AppState {
 async fn main() {
     let args: Vec<String> = std::env::args().collect();
     if args.len() < 2 {
-        eprintln!("Usage: xserv-server <model-dir> [--port PORT] [--max-batch N] [--max-seq-len N] [--swap-space-gb N]");
+        eprintln!("Usage: xserv-server <model-dir> [--port PORT] [--max-batch N] [--max-seq-len N] [--swap-space-gb N] [--tp N]");
         std::process::exit(1);
     }
 
@@ -45,6 +46,12 @@ async fn main() {
         .and_then(|i| args.get(i + 1))
         .and_then(|s| s.parse().ok())
         .unwrap_or(8);
+    let tp: usize = args.iter()
+        .position(|a| a == "--tp")
+        .and_then(|i| args.get(i + 1))
+        .and_then(|s| s.parse().ok())
+        .unwrap_or(1)
+        .max(1);
     let model_config = ModelConfig::from_file(&model_dir.join("config.json"));
     let model_max_seq_len = model_config.max_seq_len();
     if model_max_seq_len == 0 {
@@ -69,8 +76,13 @@ async fn main() {
 
     let model_dir_clone = model_dir.clone();
     std::thread::spawn(move || {
-        let mut engine = engine::Engine::load_with_swap(&model_dir_clone, max_batch, max_seq_len, swap_space_gb);
-        engine.run(rx);
+        if tp <= 1 {
+            let mut engine = engine::Engine::load_with_swap(&model_dir_clone, max_batch, max_seq_len, swap_space_gb);
+            engine.run(rx);
+        } else {
+            // Tensor-parallel path: rank-0 coordinator + worker rank threads.
+            tp_engine::run_tp(&model_dir_clone, tp, max_seq_len, rx);
+        }
     });
 
     let state = Arc::new(AppState {