model: paged KV cache with CPU swap pool, decode graph, qwen3 updates

- paged_kv_cache: new block-paged KV cache; adds a pinned-host swap pool with
  a second BlockAllocator, per-sequence Location {Gpu,Cpu}, and lossless
  swap_out/swap_in (block-granular D2H/H2D) for vLLM-style preemption.
  bytes_per_block helper exposes per-block cost for VRAM-based sizing.
- decode_graph: CUDA-graph decode path.
- qwen3/gpt2/kv_cache: paged prefill/decode forward + related updates.
- tokenizer/bins: BPE updates, new xserv-chat CLI, bench-qwen3 tweaks.

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

crates/xserv-model/src/kv_cache.rs

@@ -76,6 +76,7 @@ impl GpuKVCache {
 
     pub fn advance_seq_len(&mut self, new_tokens: usize) {
         self.seq_len += new_tokens;
+        assert!(self.seq_len <= self.max_seq_len, "KV cache seq_len ({}) exceeds max_seq_len ({})", self.seq_len, self.max_seq_len);
     }
 
     /// Get K/V cache tensors for a layer up to `seq_len` tokens: [1, num_kv_heads, seq_len, head_dim]
@@ -85,6 +86,7 @@ impl GpuKVCache {
     }
 
     pub fn get_kv_len(&mut self, layer: usize, sl: usize) -> (Tensor, Tensor) {
+        assert!(sl <= self.max_seq_len, "get_kv_len: sl ({sl}) exceeds max_seq_len ({})", self.max_seq_len);
         let hd = self.head_dim;
         let nh = self.num_kv_heads;
         let es = self.elem_size;