Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
dataset format recommendations: worth it?
#1
Thought I'd post a small recipe because a lot of threads ask similar things.

Just sharing a setup that ended up working reasonably well: Mixtral, SGLang, B200, with a lot of attention on VRAM headroom.

Feel free to tear it apart if you see something dumb.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
serving stack tinkerer
Reply
#2
I'd start with the simpler stack.
Reply
#3
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks. Once you know the plain path works, then add the faster path back in piece by piece.
routing beats arguing over one perfect model
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)