benchmarks that map to real use for Phi

[embershed99]

Wanted to compare notes with people doing similar things.

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling workstation thermals.

Would appreciate practical advice rather than theory.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[turboyard94]

Good point. That matches what I saw on GB200. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[batchwire]

Can you fill in a bit more context? Are you testing this on B200 or something else?

[cachebench]

following this because I'm in the same boat. At this point the real bottleneck is my patience.

[fastbench]

That matches what I was seeing. That matches what I saw on B200. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[labline]

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.

[latentscope35]

What worked for me was pretty simple. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[thetapath]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency.

[emberpeak]

Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher.

[fusedtinker]

worth checking the driver first.

I'm happy to test one more variant if you want a second data point.