✨ feat: add XAttention BSA support to bench_offload.py

- Add --model parameter (default: Llama-3.1-8B-Instruct)
- Add --enable-xattn flag for XAttention BSA sparse prefill
- Add --xattn-threshold and --xattn-stride parameters
- Change default num-gpu-blocks from 6 to 4
- Add benchmark results doc with Full vs XAttn comparison (32K/128K)

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

@@ -27,6 +27,7 @@ Nano-vLLM is a lightweight vLLM implementation (~1,200 lines) for fast offline L
 | [`docs/chunked_attention_solutions.md`](docs/chunked_attention_solutions.md) | 🔧 SOLUTIONS: Chunked attention 准确性问题的代码分析和解决方案 |
 | [`docs/nsys_wrong_event_order_bug.md`](docs/nsys_wrong_event_order_bug.md) | 🐛 NSYS BUG: Ring buffer pipeline 触发 nsys 时间戳乱序问题的调试记录 |
 | [`docs/cpu_scheduling_latency_analysis.md`](docs/cpu_scheduling_latency_analysis.md) | ⚡ PERF: CPU 调度延迟分析，kernel 间隙来源，GPU 利用率优化方向 |
+| [`docs/bench_offload_results.md`](docs/bench_offload_results.md) | 📊 BENCH: CPU offload 性能测试结果，Full vs XAttention 对比 (32K/128K) |
 
 ## Rules Index