113
edits
Raphael0202 (talk | contribs) |
Raphael0202 (talk | contribs) |
||
Line 18: | Line 18: | ||
** New server | ** New server | ||
*** Models are memory hungry, at least 32 GB of RAM is needed. | *** Models are memory hungry, at least 32 GB of RAM is needed. | ||
*** GPU servers deliver the best performances for prediction, but are rather expensive. Given the current load, CPU servers are enough. | *** GPU servers deliver the best performances for prediction, but are rather expensive. Given the current load, CPU servers are enough. High-performance CPU are however needed. 8 cores at least (the more, the better). | ||
*** Disk: speed is only important when loading model from disk, which only occurs at startup. SSDs are fine. 500 GB of space should be ok. | *** Disk: speed is only important when loading model from disk, which only occurs at startup. SSDs are fine. 500 GB of space should be ok. | ||
* New producer platform | * New producer platform |