Alexander Whedon
@alex_whedon
Building better algorithms.
Co-Founder at @subquadratic
가입 November 2024
75 팔로잉 중 25.1K 팬
We've partnered with Appen to evaluate the benchmarks we published last week.
Results are in and we've actually improved across the board.
Link below to the full report.
@AppenResearch independently evaluated @subquadratic's SSA kernel - a learned sparse attention mechanism designed to reduce the quadratic scaling limitations of full attention.
Results at 1M-token context lengths:
- 56.2× wall clock speedup vs. FA2
- 62.8× FLOP reduction (validated via torch.profiler, <4% variance from theoretical)
- 95.6% average score across RULER tasks at 128K
- 86.2% average score on the hardest MRCR 8-needle bucket (512K–1M contexts)
- 81.8% SWE-Bench Verified resolved rate
Full report:
더 보기
