Zijie Tian
|
af4da454ba
|
📊 docs: add XAttention offload profiling analysis for 32K context
- Profile XAttn vs Full attention using nsys NVTX markers
- Key finding: estimate (41%) + find_blocks (37%) dominate, compute only 21%
- Chunk7 comparison: XAttn (38ms) vs Full (35ms) - XAttn slightly slower
- Identify optimization opportunities: reduce find_blocks overhead, merge estimate passes
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>
|
2026-02-05 02:49:59 +08:00 |
|