best small quant that still feels smart

[vrambandit]

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

I'm comparing two approaches here: keep it simple on A6000, or squeeze more out of the stack and deal with the complexity.

Interested in tradeoffs more than fan loyalty.

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

[cudaline]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

[benchplease]

following this because I'm in the same boat.

[northquill]

same here on my side. I keep promising myself this is the last rebuild.

[rasterbench]

Good point. I don't think your conclusion is far off.

[llmarch51]

Good point. That matches what I saw on M3 Max.

[fastquill74]

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[fusedtinker]

What worked for me was pretty simple. On B200, 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.

[benchplease]

same here on my side.