Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill bottlenecks on longer prompts on GB200
#1
This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate quant drift until they actually try to run this stuff for more than one afternoon.

Curious whether that lines up with what other people are seeing.

I care more about stability than squeezing the last possible tokens/sec out of it.
Reply


Messages In This Thread
prefill bottlenecks on longer prompts on GB200 - by cacheworks - 09-15-2026, 09:03 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)