+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Long Context / Memory (https://www.datasculpting.ai/inference/forumdisplay.php?fid=64)
+--- Thread: long context that stayed useful (/showthread.php?tid=489)
Pages:
1
2
Re: long context that stayed useful - visionforge - 10-02-2026
Tried to reproduce it just now. On dual 3090 with PyTorch, I saw basically the same behavior. The main thing that moved was latency, not quality.