title: two prefill lines on the L4 without the cache, 4,096 shared tokens
source: manuals/sglang-101/capture/gpu/out-l4/server-prefix-no-radix-cache.log
lang: text
note: Every token is new, and the pending tokens wait for the next chunk.
---
[2026-10-17 14:35:48] Prefill batch, #new-seq: 2, #new-token: 4096, #cached-token: 0, token usage: 0.68, #running-req: 1, #queue-req: 0, #pending-token: 5527, cuda graph: True, input throughput (token/s): 1632.42
[2026-10-17 14:35:50] Prefill batch, #new-seq: 2, #new-token: 4096, #cached-token: 0, token usage: 0.74, #running-req: 2, #queue-req: 0, #pending-token: 1431, cuda graph: True, input throughput (token/s): 1634.70
