[2026-10-17 15:54:33] Prefill batch, #new-seq: 8, #new-token: 4096, #cached-token: 1, token usage: 0.34, #running-req: 1, #queue-req: 0, #pending-token: 513, cuda graph: True, input throughput (token/s): 3509.80
[2026-10-17 15:54:34] Prefill batch, #new-seq: 8, #new-token: 3583, #cached-token: 0, token usage: 0.34, #running-req: 8, #queue-req: 0, #pending-token: 0, cuda graph: True, input throughput (token/s): 3503.78
[2026-10-17 15:54:35] Decode batch, #running-req: 16, #token: 8240, token usage: 0.34, cuda graph: True, gen throughput (token/s): 2.62, #queue-req: 0
[2026-10-17 15:54:37] Decode batch, #running-req: 16, #token: 8880, token usage: 0.37, cuda graph: True, gen throughput (token/s): 231.07, #queue-req: 0
[2026-10-17 15:54:40] Decode batch, #running-req: 16, #token: 9520, token usage: 0.40, cuda graph: True, gen throughput (token/s): 229.85, #queue-req: 0