Appen Research(@AppenResearch):@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:

Appen Research

@AppenResearch

Human data for frontier AI. Research and insights from Appen.

加入 May 2026

210 正在关注 274 粉丝

Appen Research@AppenResearch

2026.05.12 17:20

@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:

显示更多