+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Dataset Creation / Curation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=56)
+--- Thread: embedding model you trust on 7900 XTX (/showthread.php?tid=993)
Pages:
1
2
Re: embedding model you trust on 7900 XTX - torchkite - 10-18-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: embedding model you trust on 7900 XTX - batchsize - 10-19-2026
Quote:I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not qual
I'd start with the simpler stack.