✨ feat: integrate sparse policy architecture into GPU-only mode

- Add compute_prefill() and compute_decode() GPU-only methods to SparsePolicy base class
- Implement GPU-only methods in FullAttentionPolicy using flash_attn
- Add sparse_policy parameter to GPUOnlyManager
- Update create_kvcache_manager() to create FullAttentionPolicy for GPU-only mode
- Route GPU-only attention through sparse_policy in attention.py
- Pass kvcache_manager to context for policy access
- Add --enable-policy flag to bench.py for testing
- Handle warmup phase when kvcache_manager is not yet allocated

This allows GPU-only mode to use the same policy architecture as CPU offload mode,
enabling future sparse attention implementations (Quest, XAttention) in GPU-only mode.

Performance verified: ~4890 tok/s (unchanged from baseline)

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

bench.py

@@ -40,6 +40,8 @@ def bench_prefill(llm, num_seqs, input_len):
 
 def main():
     import argparse
+    from nanovllm.config import SparsePolicyType
+
     parser = argparse.ArgumentParser(description="Benchmark nanovllm GPU performance")
     parser.add_argument("--model", type=str, default="~/models/Llama-3.1-8B-Instruct",
                         help="Model path (default: ~/models/Llama-3.1-8B-Instruct)")
@@ -48,18 +50,28 @@ def main():
     parser.add_argument("--max-len", type=int, default=32*1024, help="Max model length (default: 32K)")
     parser.add_argument("--bench-decode", action="store_true", help="Run decode benchmark (default: prefill only)")
     parser.add_argument("--bench-all", action="store_true", help="Run both prefill and decode benchmarks")
+    # Sparse policy option (GPU-only mode now supports policy routing)
+    parser.add_argument("--enable-policy", action="store_true",
+                        help="Enable sparse policy routing (FullAttentionPolicy by default)")
     args = parser.parse_args()
 
     path = os.path.expanduser(args.model)
     max_len = args.max_len
 
-    print(f"\n[nanovllm GPU] max_len={max_len}")
+    # Configure sparse policy
+    if args.enable_policy:
+        sparse_policy = SparsePolicyType.FULL
+        print(f"\n[nanovllm GPU + Policy] sparse_policy=FULL, max_len={max_len}")
+    else:
+        sparse_policy = None
+        print(f"\n[nanovllm GPU] max_len={max_len}")
 
     llm = LLM(
         path,
         enforce_eager=False,
         max_model_len=max_len,
         max_num_batched_tokens=max_len,
+        sparse_policy=sparse_policy,
     )
 
     # Warmup