Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Attention Kernel Performance Evaluation on Sparse-Attention Micro-Benchmark N=600 (test)

0.42Latency (ms)

TempoNet

0.40960.47980.550.6202Feb 20, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
0.420.62
2026.02
0.650.95
2026.02
0.681