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

Context sequences

Benchmarks

Task NameDataset NameSOTA ResultTrend
Time to First Token (TTFT) measurementContext sequences 32K-256K vLLM 0.18.0 / 0.20.0 (online-serving)
TTFT (Dense, s)2.944
7
Showing 1 of 1 rows