301 B
301 B
Qwen30 real latency case audit
Prefill-only: True.
| Objective | Real winner | Value (ms) |
|---|---|---|
| ttft_ms:pooled_mean_ms | tp4_mns32 | 113.40 |
| ttft_ms:pooled_p90_ms | tp4_mns32 | 114.69 |
| e2e_ms:pooled_mean_ms | tp4_mns32 | 113.44 |
| e2e_ms:pooled_p90_ms | tp4_mns32 | 114.74 |