title: output tokens per second from three clients
source: manuals/vllm-101/capture/gpu/out-l4/bench-client-bias.txt
lines: 18-24
lang: text
note: Compare the columns at 16 and 64 users, then look at the first SGLang round at one user.
---
Output throughput in tok/s, two rounds per cell:

users   temperature   SGLang client    vllm bench       vllm bench, Rust
1       0             39.9, 31.0       32.0, 31.9       32.2, 31.8
16      0             218, 216         222, 222         223, 223
64      0             359, 348         379, 377         371, 365
64      0.7           331, 343         360, 363         356, 353
