title: two prefill lines on the L4 with the cache, 2,048 shared tokens
source: manuals/sglang-101/capture/gpu/out-l4/server-prefix-default.log
lang: text
note: Read #new-token against #cached-token.
---
[2026-10-17 13:21:05] Prefill batch, #new-seq: 3, #new-token: 405, #cached-token: 12952, token usage: 0.58, #running-req: 1, #queue-req: 0, #pending-token: 0, cuda graph: True, input throughput (token/s): 1452.28
[2026-10-17 13:21:06] Prefill batch, #new-seq: 4, #new-token: 546, #cached-token: 17269, token usage: 0.58, #running-req: 4, #queue-req: 0, #pending-token: 0, cuda graph: True, input throughput (token/s): 2532.09
