Commit Graph

1 Commits

Author SHA1 Message Date
Zijie Tian
0619accd1c 📝 docs: add CPU scheduling latency analysis for chunked attention
- Document kernel gap analysis showing 77-81% CPU scheduling overhead
- Identify GPU utilization at 12.8% with potential to reach 39.5%
- Outline optimization directions: CUDA Graph, Triton fusion, C++ extension
- Add documentation index entry in CLAUDE.md

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>
2026-01-27 03:42:12 +08:00