medium10 pts · first answer countsmodel-servinghardware
Many small models on one A100
You have seven small models, each needing under 8 GB, and want strong isolation between them on one A100 80GB. Which feature fits?
Discussion 0
Join free to post in the discussion.
Related questions
- When batch inference fitsMLOps Engineer
- Traffic before the model has loadedMLOps Engineer
- Why export a model to ONNXMLOps Engineer
- Protocol for internal inference callsMLOps Engineer
- Matching the GPU to the jobMLOps Engineer
- Memory on common data-centre GPUsMLOps Engineer
- Latency and throughputMLOps Engineer
- What TTFT measuresMLOps Engineer