+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: prefill bottlenecks on longer prompts (/showthread.php?tid=1432)
Pages:
1
2
Re: prefill bottlenecks on longer prompts - byteyard - 10-19-2026
Appreciate the detail. I don't think your conclusion is far off.
Re: prefill bottlenecks on longer prompts - quiettoken - 10-19-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: prefill bottlenecks on longer prompts - visionforge - 10-19-2026
I'd approach it in a boring order. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.