Retrieval on TREC-COVID (Latency Metrics)
6.05H2D 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|=171K, |Q|=502026.05 | 6.05 | 0.63 | 118.5 | 0.04 | 2.52 | 1.8 | 92 |