[None][bugfix] Restore _get_window_size_to_layers method on KVCacheManager

The method was removed during the VSWA extraction refactor but is still
called by disaggregated serving code (kv_extractor, test_mamba_transfer).
Re-add it as a thin wrapper around the extracted standalone function.

Signed-off-by: Yueh-Ting Chen <yueh.ting.chen@gmail.com>

Author: eopXD

tensorrt_llm/_torch/pyexecutor/resource_manager/kv_cache_manager.py

@@ -41,7 +41,11 @@
 from ..scheduler import ScheduledRequests
 from .base import BaseResourceManager, request_context
 from .kv_cache_spec_ops import _update_kv_cache_draft_token_location, get_pp_layers
-from .vswa import calculate_max_num_blocks_for_vswa, validate_and_adjust_attention_windows
+from .vswa import (
+    calculate_max_num_blocks_for_vswa,
+    get_window_size_to_layers,
+    validate_and_adjust_attention_windows,
+)
 
 if TYPE_CHECKING:
     from tensorrt_llm._torch.attention_backend.interface import AttentionMetadata
@@ -662,6 +666,9 @@ def get_cache_bytes_per_token(self):
             )
         return cache_size_bytes_per_token
 
+    def _get_window_size_to_layers(self) -> Dict[int, List[int]]:
+        return get_window_size_to_layers(self.max_attention_window_vec, self.num_local_layers)
+
     def calculate_max_num_blocks(
         self,
         kv_cache_config: KvCacheConfig,