Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
routing between local and hosted: what are you seeing?
#7
Quote:A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Once

I hit almost the same issue last night.

I'm happy to test one more variant if you want a second data point.
throughput matters, but tail latency matters too
Reply


Messages In This Thread
Re: routing between local and hosted: what are you seeing? - by batchsize - 09-10-2026, 03:28 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)