medium10 pts · first answer countsmodel-servinglatencyretrieval
Cross-encoder reranker is slow
A cross-encoder reranker scores every one of 1,000 retrieved passages per query and adds 2 seconds of latency. What is the usual fix?
Discussion 0
Join free to post in the discussion.
Related questions
- When batch inference fitsMLOps Engineer
- Traffic before the model has loadedMLOps Engineer
- What p99 latency meansMLOps Engineer
- Why export a model to ONNXMLOps Engineer
- Protocol for internal inference callsMLOps Engineer
- Average latency looks fineMLOps Engineer
- Service health basicsMLOps Engineer
- Why track time to first tokenMLOps Engineer