Inference
non-AI thing you built recently - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: Off Topic (https://www.datasculpting.ai/inference/forumdisplay.php?fid=27)
+--- Thread: non-AI thing you built recently (/showthread.php?tid=369)

Pages: 1 2


Re: non-AI thing you built recently - routecraft - 10-05-2026

Quote:Need a little more detail here. What model, what runtime, and roughly what context size?

following this because I'm in the same boat.


Re: non-AI thing you built recently - cobaltlab - 10-06-2026

Appreciate the detail. I don't think your conclusion is far off.


Re: non-AI thing you built recently - tinycontext - 10-06-2026

Quote:Appreciate the detail. I don't think your conclusion is far off.

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at batch size. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

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


Re: non-AI thing you built recently - thetapath - 10-06-2026

worth checking the driver first.


Re: non-AI thing you built recently - northcraft90 - 10-09-2026

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Not glamorous advice, but repeatable baselines save a lot of time.