Vector Databases discussion on Threadripper box

[vectorember]

Did a bit of testing and thought I'd post the result here.

After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around quant drift.

Happy to post more details if anyone wants them.

[routeforge64]

I'd approach it in a boring order. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[fastfield4]

Maybe, but I had the opposite result. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[amberhall]

What worked for me was pretty simple. On 5090, 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.

[minthall]

That matches what I was seeing. The pattern around continuous batching has been pretty similar for me.

[deltagrid]

that fixed it for me too.

[tinycontext]

I'd start with the simpler stack. I keep promising myself this is the last rebuild.

[fusedriver]

following this because I'm in the same boat.

[tinycontext]

That matches what I was seeing. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

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

[bytegarden73]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.