+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: RAG (https://www.datasculpting.ai/inference/forumdisplay.php?fid=58)
+--- Thread: search and retrieval tuning tips for Mixtral (/showthread.php?tid=81)
Pages:
1
2
Re: search and retrieval tuning tips for Mixtral - quietarch - 09-02-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?
Re: search and retrieval tuning tips for Mixtral - kernelghost - 09-02-2026
Good point. The pattern around tail latency has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: search and retrieval tuning tips for Mixtral - routeforge64 - 09-03-2026
following this because I'm in the same boat.
Re: search and retrieval tuning tips for Mixtral - orbitgarden - 09-04-2026
My first guess would be this: On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: search and retrieval tuning tips for Mixtral - cacheline - 09-04-2026
Good point. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.