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

vLLM serving benchmark

Benchmarks

Task NameDataset NameSOTA ResultTrend
Large Language Model ServingvLLM serving benchmark 128 prompts, 32 pre-fill tokens, 256 generation tokens
TTFT (ms)76
9
Showing 1 of 1 rows