📝 docs: add XAttention density types documentation

Document the difference between compute density (BSA block level)
and communication density (CPU block level).

Key finding: Even with 37% compute density, comm density can be 100%
due to any() aggregation across heads/Q-positions spreading sparse
blocks across all CPU blocks.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

CLAUDE.md

@@ -43,6 +43,7 @@ Nano-vLLM is a lightweight vLLM implementation (~1,200 lines) for fast offline L
 | [`docs/gpuonly_density_alignment_test.md`](docs/gpuonly_density_alignment_test.md) | ✅ TEST: Density 对齐验证 (GPU-only + Offload, 4K-64K)，xattn_estimate vs KV chunking 完全一致 |
 | [`docs/xattn_memory_benchmark.md`](docs/xattn_memory_benchmark.md) | 📊 BENCH: XAttention 内存基准测试，Qwen3-0.6B 32K 在 24GB 显存可行 (gpu-util=0.28) |
 | [`docs/xattn_offload_stream_sync_fix.md`](docs/xattn_offload_stream_sync_fix.md) | 🐛 FIX: XAttention Offload stream 同步 bug，Pass1/Pass2 K 数据不一致，compute_stream 包装 |
+| [`docs/xattn_density_types.md`](docs/xattn_density_types.md) | 📊 Compute vs Comm density: BSA block (128) vs CPU block (4096) 粒度，聚合效应导致 comm=100% |
 
 ## Rules Index