Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
synthetic data for support bots with SGLang
#1
Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about continuous batching.

Would rather learn from your scars than collect my own all at once.

I care more about stability than squeezing the last possible tokens/sec out of it.
routing beats arguing over one perfect model
Reply
#2
Good point. That matches what I saw on A6000. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
curious and caffeinated
Reply
#3
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
serving stack tinkerer
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)