Best practices to deal with serverless throttling
Since we are not the only ones dealing with serverless throttling (https://discord.com/channels/912829806415085598/1413624731533443137/1425369322527920211), perhaps there are already best practices/recommendations to mitigate the issue? For example, run more workers, use different GPUs, use Instant Clusters, put some parameters in place, etc.?
0 Replies