Inference
search and retrieval tuning tips for DeepSeek - Printable Version

+- 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 DeepSeek (/showthread.php?tid=1448)



Re: search and retrieval tuning tips for DeepSeek - fusedhall56 - 10-18-2026

What exact setup are you running? Are you testing this on Threadripper box or something else?


Re: search and retrieval tuning tips for DeepSeek - deltastation - 10-18-2026

A couple things I'd check first. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.


Re: search and retrieval tuning tips for DeepSeek - cacheworks - 10-18-2026

Quote:A couple things I'd check first. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.


Re: search and retrieval tuning tips for DeepSeek - bytelab - 10-18-2026

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed.


Re: search and retrieval tuning tips for DeepSeek - audionode8 - 10-18-2026

that fixed it for me too.


Re: search and retrieval tuning tips for DeepSeek - kernelghost - 10-19-2026

same here on my side.


search and retrieval tuning tips for DeepSeek - modbench - 10-19-2026

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about prefill/decode split.

Would rather learn from your scars than collect my own all at once.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.


Re: search and retrieval tuning tips for DeepSeek - tinycontext - 10-19-2026

Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.