✨ 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>

nanovllm/kvcache/gpu_manager.py

@@ -7,13 +7,16 @@ the KVCacheManager interface.
 """
 
 from collections import deque
-from typing import List, Tuple, Dict, Optional
+from typing import List, Tuple, Dict, Optional, TYPE_CHECKING
 import torch
 from torch import Tensor
 
 from nanovllm.engine.sequence import Sequence
 from nanovllm.kvcache.base_manager import KVCacheManager
 
+if TYPE_CHECKING:
+    from nanovllm.kvcache.sparse.policy import SparsePolicy
+
 
 class Block:
     """Physical block in GPU memory."""
@@ -50,17 +53,28 @@ class GPUOnlyManager(KVCacheManager):
     all data stays on GPU at fixed addresses.
     """
 
-    def __init__(self, num_blocks: int, block_size: int):
+    def __init__(
+        self,
+        num_blocks: int,
+        block_size: int,
+        sparse_policy: Optional["SparsePolicy"] = None,
+    ):
         """
         Initialize GPU-only manager.
 
         Args:
             num_blocks: Total number of blocks to manage
             block_size: Tokens per block (default 256)
+            sparse_policy: Optional sparse attention policy for GPU-only mode
         """
         self._block_size = block_size
         self._num_blocks = num_blocks
 
+        # Sparse policy for GPU-only mode (optional)
+        self.sparse_policy = sparse_policy
+        # No offload engine in GPU-only mode
+        self.offload_engine = None
+
         # Block metadata
         self.blocks: List[Block] = [Block(i) for i in range(num_blocks)]