Latency and Speed Evaluation on Quora Retrieval
19.7H2D Latency (ms)AgentIR
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| AgentIRHardware=A100 40 GB, Batch size=all judged queries, chunked when B · N · 4B > 16 GB, k=100, |D|=523K, |Q|=10,0002026.05 | 19.7 | 21.8 | 3,129 | 1.45 | 0.32 | 5 | 90.2 |