+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: Off Topic (https://www.datasculpting.ai/inference/forumdisplay.php?fid=27)
+--- Thread: desk setup thread on 5090 (/showthread.php?tid=168)
Pages:
1
2
desk setup thread on 5090 - promptspark58 - 09-07-2026
This keeps coming up in conversation so I figured I'd start a thread.
One thing I keep noticing is that people underestimate MoE serving until they actually try to run this stuff for more than one afternoon.
Maybe obvious to some of you, but it clicked for me this week.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: desk setup thread on 5090 - mintquill - 09-08-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Once you know the plain path works, then add the faster path back in piece by piece.
Re: desk setup thread on 5090 - orbitline - 09-08-2026
Quote:A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Once you kn
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. Not glamorous advice, but repeatable baselines save a lot of time.
Re: desk setup thread on 5090 - phaseport36 - 09-09-2026
that fixed it for me too.
Re: desk setup thread on 5090 - batchyard - 09-09-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Re: desk setup thread on 5090 - cacheline - 09-10-2026
I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: desk setup thread on 5090 - nanogarden - 09-10-2026
A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: desk setup thread on 5090 - phasestream53 - 09-10-2026
I hit almost the same issue last night.
Re: desk setup thread on 5090 - routecrate - 09-11-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4.
Re: desk setup thread on 5090 - mangoquill - 09-13-2026
Quote:A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at INT4.
Not sure I agree there. I've seen people blame tool calling when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.