Files
nano-vllm/nanovllm
Zijie Tian 5eb35982bf 🔧 feat: add density statistics tracking to sparse policies
Add statistics tracking to compare block selection between policies:
- XAttentionBSAPolicy: track available/selected blocks per chunk
- FullAttentionPolicy: track total blocks (always 100% density)
- Add reset_stats(), get_density_stats(), print_density_stats() methods
- Use logger.debug for per-chunk density logging

Results on 32K niah_single_1:
- Full: 100% density across all chunks
- XAttn BSA: 90% -> 73% density (saves ~25-30% blocks in later chunks)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 08:53:22 +08:00
..
2025-06-15 10:36:45 +08:00
2025-06-15 01:31:24 +08:00
2025-08-31 22:55:34 +08:00