📈 feat: add MemoryObserver for GPU-CPU communication tracking

Implement MemoryObserver to track memory transfers between GPU and CPU:
- H2D (Host to Device): CPU → GPU transfers
- D2H (Device to Host): GPU → CPU transfers
- D2D (Device to Device): GPU buffer copies
- Supports prefill/decode phase separation

Integration points in offload_engine.py:
- load_to_slot_layer: H2D with is_prefill parameter
- offload_slot_layer_to_cpu, offload_prefill_buffer_async: D2H
- write_to_prefill_buffer, write_to_decode_buffer: D2D
- load_block_sample_from_cpu, load_block_full_from_cpu: H2D

Add bench_offload.py integration for memory stats printing.

Benchmark results (Llama-3.1-8B, 64K context):
- Full Policy: Prefill H2D 262.13 GB
- XAttention: Prefill H2D 386.62 GB (1.48x)

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>

CLAUDE.md

@@ -31,6 +31,8 @@ Nano-vLLM is a lightweight vLLM implementation (~1,200 lines) for fast offline L
 | [`docs/cpu_offload_optimization_strategies.md`](docs/cpu_offload_optimization_strategies.md) | 🚀 OPT: CPU offload 优化策略：chunk size、CUDA Graph、前沿研究(InfiniGen/ShadowKV) |
 | [`docs/gpu_only_xattn_guide.md`](docs/gpu_only_xattn_guide.md) | 🚀 GPU-Only XAttention: 内存预分配、性能分析 (32K +15%, 64K +41%)、CUDA Graph 限制 |
 | [`docs/xattn_performance_analysis.md`](docs/xattn_performance_analysis.md) | 📊 XAttention 性能分析: NVTX 标记、block size 影响、estimate vs compute 耗时对比 |
+| [`docs/observer_architecture.md`](docs/observer_architecture.md) | 📊 Observer 架构: InferenceObserver (TTFT/TPOT)、MemoryObserver (H2D/D2H/D2D) 设计 |
+| [`docs/memory_communication_benchmark.md`](docs/memory_communication_benchmark.md) | 📊 通信量测试: Full vs XAttention 通信量对比 (32K/64K)、阶段分离统计 |
 
 ## Rules Index