WIP: Enhance sparse attention with density tracking and block selection improvements

- Added analysis documentation for xattn density alignment.
- Refactored ModelRunner to pre-allocate policy metadata buffers regardless of CPU offload configuration.
- Updated FullAttentionPolicy and SparsePolicy to accept query and key tensors for block selection.
- Enhanced QuestPolicy to utilize query tensor for block selection and improved handling of selected blocks.
- Expanded XAttentionBSAPolicy to support chunked prefill and improved attention score computation with historical and current chunk handling.
- Introduced DensityObserver to track compute and communication density for sparse attention layers.
- Updated attention layer to ensure block selection is always called, improving robustness in first chunk scenarios.
- Added tests for attention kernel behavior with enhanced input patterns.

nanovllm/kvcache/sparse/full_policy.py

@@ -47,6 +47,8 @@ class FullAttentionPolicy(SparsePolicy):
         available_blocks: List[int],
         offload_engine: "OffloadEngine",
         ctx: PolicyContext,
+        q: torch.Tensor,
+        k: torch.Tensor,
     ) -> List[int]:
         """Return all blocks - no sparsity."""
         # Update statistics (only for layer 0 to avoid overcounting)