10-15-2026, 01:59 PM
Good point. I don't think your conclusion is far off.
|
good hosted AI app that still respects privacy on A6000
|
|
10-15-2026, 01:59 PM
Good point. I don't think your conclusion is far off.
10-16-2026, 02:31 PM
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
10-17-2026, 03:14 AM
Quote:Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quali I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at speculative decoding. Not glamorous advice, but repeatable baselines save a lot of time. |
|
« Next Oldest | Next Newest »
|