Zijie Tian f6ac4ccdde ✨ feat: add DensityObserver for XAttention sparse attention density tracking ...

- Add DensityObserver class to track per-layer density statistics
- Integrate DensityObserver into compute_prefill for GPU-only mode
- Fix stride parameter not being passed to xattn_estimate
- Add density statistics output to test_ruler.py for XATTN_BSA
- Add comprehensive density benchmark documentation

Key changes:
- nanovllm/utils/density_observer.py: New Observer for density tracking
- xattn_bsa.py: Add stride param to xattn_estimate, integrate DensityObserver
- test_ruler.py: Enable DensityObserver and print summary for XATTN_BSA
- docs/xattn_density_benchmark.md: Benchmark results for 4K-32K contexts

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-30 16:26:56 +08:00

34 KiB

Raw Blame History

View Raw