server: support GptOss in TP engine + benchmark script

- tp_engine.rs: TpModel enum dispatches between Qwen3 and GptOss based on
  config.is_moe(). Server auto-detects model type on startup.
- tools/run_gpt_oss_bench.sh: one-click benchmark comparing xserv (TP=2)
  vs llama.cpp (BF16 GGUF) on GSM8K quality + speed

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/xserv-server/src/tp_engine.rs

@@ -19,8 +19,8 @@ use std::thread;
 
 use xserv_distributed::{TpContext, UniqueId};
 use xserv_model::loader;
-use xserv_model::{sample, ModelConfig, PagedKVCache, Qwen3, BLOCK_SIZE};
-use xserv_tensor::{DType, Device};
+use xserv_model::{sample, GptOss, ModelConfig, PagedKVCache, Qwen3, BLOCK_SIZE};
+use xserv_tensor::{DType, Device, Tensor};
 use xserv_tokenizer::Tokenizer;
 
 use crate::engine::{GenerateEvent, GenerateRequest};
@@ -34,8 +34,29 @@ enum TpCommand {
     Shutdown,
 }
 
+enum TpModel {
+    Qwen3(Qwen3),
+    GptOss(GptOss),
+}
+
+impl TpModel {
+    fn forward_prefill_paged(&self, tokens: &[u32], slot: usize, cache: &mut PagedKVCache) -> Tensor {
+        match self {
+            TpModel::Qwen3(m) => m.forward_prefill_paged(tokens, slot, cache),
+            TpModel::GptOss(m) => m.forward_prefill_paged(tokens, slot, cache),
+        }
+    }
+
+    fn forward_decode_paged(&self, tokens: &[u32], positions: &[usize], slots: &[usize], cache: &mut PagedKVCache) -> Tensor {
+        match self {
+            TpModel::Qwen3(m) => m.forward_decode_paged(tokens, positions, slots, cache),
+            TpModel::GptOss(m) => m.forward_decode_paged(tokens, positions, slots, cache),
+        }
+    }
+}
+
 struct RankCtx {
-    model: Qwen3,
+    model: TpModel,
     cache: PagedKVCache,
 }
 
@@ -49,9 +70,13 @@ fn build_rank(
     tp: Option<Arc<TpContext>>,
 ) -> RankCtx {
     let weights = loader::load_model_dir(model_dir, Device::Cpu);
-    let model = Qwen3::from_weights_tp(config.clone(), weights, rank, world, device, tp);
+    let model = if config.is_moe() {
+        TpModel::GptOss(GptOss::from_weights_tp(config.clone(), weights, rank, world, device, tp))
+    } else {
+        TpModel::Qwen3(Qwen3::from_weights_tp(config.clone(), weights, rank, world, device, tp))
+    };
     let local_kv = config.num_kv_heads() / world;
-    let max_blocks_per_seq = max_seq_len.div_ceil(BLOCK_SIZE);
+    let max_blocks_per_seq = (max_seq_len + BLOCK_SIZE - 1) / BLOCK_SIZE;
     let total_blocks = max_blocks_per_seq + 8;
     let cache = PagedKVCache::new_tp(
         config, local_kv, total_blocks, 0, 4, max_blocks_per_seq, DType::BF16, device,