VOGONS


First post, by ElectroSoldier

User metadata
Rank Oldbie
Rank
Oldbie

Given how an inference model stresses a GPU so much more than any game does how when will site like this start using them to benchmark PCs you think?
Im thinking MLPerf Inference, HuggingFace Optimum etc

Reply 1 of 1, by cyclone3d

User metadata
Rank l33t++
Rank
l33t++

The thing about benchmarks is that they have to be scripted.

Run the same query on a inference model multiple times and the results will vary and thus the load on the system will not be perfectly predictable.

Yamaha modified setupds and drivers
Yamaha XG repository
YMF7x4 Guide
Aopen AW744L II SB-LINK