10-18-2026, 10:43 PM
Quote:Quote:that fixed it for me too.
that fixed it for me too.
I'm happy to test one more variant if you want a second data point.
|
flux pipeline local tips
|
|
10-18-2026, 10:43 PM
Quote:Quote:that fixed it for me too. that fixed it for me too. I'm happy to test one more variant if you want a second data point.
10-18-2026, 11:17 PM
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.
10-19-2026, 02:51 AM
Quote:Interesting, I hadn't tried that. That matches what I saw on A6000. That matches what I was seeing. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
curious and caffeinated
10-19-2026, 03:34 AM
Interesting, I hadn't tried that. That matches what I saw on A6000.
small models can still be good
|
|
« Next Oldest | Next Newest »
|