Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
what are you all running this week
#1
Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of SGLang and GB200 felt surprisingly usable once I tuned around INT4.

If someone wants the exact settings I can clean them up and post them.
Reply
#2
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Reply
#3
A couple things I'd check first. On 4090, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
small models can still be useful
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)