dataset format recommendations: anyone testing this?

[plainline]

Spent some time on this today and wanted to compare notes.

I'm comparing two approaches here: keep it simple on 5090, or squeeze more out of the stack and deal with the complexity.

What would you pick if you had to live with it for a few months?

[audiorunner74]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[quantsupply]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at structured output.

[forgemixer]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at structured output.

worth checking the driver first.

[routecraft]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals. Not glamorous advice, but repeatable baselines save a lot of time.

[plainworks]

I'd start with the simpler stack.

[quantsupply]

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.

[phasenode]

worth checking the driver first.

[macroforge]

I'd start with the simpler stack.

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

[routecraft]

Not sure I agree there. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.