Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
simple router policy ideas with PyTorch
#11
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. Once you know the plain path works, then add the faster path back in piece by piece.
Reply
#12
I don't think that's the whole story. I get why that seems right, but on M3 Max the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
Reply
#13
I'd start with the simpler stack.

I'm happy to test one more variant if you want a second data point.
throughput matters, but tail latency matters too
Reply
#14
Quote:I'd start with the simpler stack.

following this because I'm in the same boat.
Reply
#15
Good point. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Reply


Forum Jump:


Users browsing this thread: 3 Guest(s)