Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Training Throughput on Synthetic 8192-token context (train)

229,957Training Throughput (tok/s)

Full-sequence attention

148,856.76169,911.63190,966.5212,021.37Jul 2, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
229,957
2026.07
223,825
2026.07
166,849
2026.07
151,976