+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Vector Databases (https://www.datasculpting.ai/inference/forumdisplay.php?fid=60)
+--- Thread: Help with Vector Databases for DeepSeek (/showthread.php?tid=1091)
Pages:
1
2
Help with Vector Databases for DeepSeek - macronest - 10-13-2026
Curious what people here are seeing.
I'm mostly working with DeepSeek in MLX on GB200. The part I'm trying to understand is prefix caching.
If you've tested something similar, what did you keep and what did you stop bothering with?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: Help with Vector Databases for DeepSeek - fastfield4 - 10-14-2026
Good point. I ended up in about the same place using MLX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
I'm happy to test one more variant if you want a second data point.
Re: Help with Vector Databases for DeepSeek - cozywire - 10-14-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at embeddings.
Re: Help with Vector Databases for DeepSeek - emberrunner - 10-14-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Once you know the plain path works, then add the faster path back in piece by piece.
Re: Help with Vector Databases for DeepSeek - deltagrid - 10-14-2026
Ran a quick check on my box. On Threadripper box with Ollama, I saw basically the same behavior. I expected the model choice to matter more than it did.
Re: Help with Vector Databases for DeepSeek - tinycontext - 10-16-2026
subscribed, curious where this lands.
Re: Help with Vector Databases for DeepSeek - deltagrid - 10-16-2026
A couple questions before I guess too hard. Are you testing this on dual 3090 or something else?
Re: Help with Vector Databases for DeepSeek - macronest - 10-17-2026
Appreciate the detail. The pattern around MoE serving has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Help with Vector Databases for DeepSeek - quietsupply11 - 10-17-2026
Quote:Appreciate the detail. The pattern around MoE serving has been pretty similar for me. Worth rechecking your defaults though, because one bad assumptio
following this because I'm in the same boat.
Re: Help with Vector Databases for DeepSeek - edgecoast - 10-18-2026
Quote:[quote]Appreciate the detail. The pattern around MoE serving has been pretty similar for me. Worth rechecking your defaults though, because one bad as
Appreciate the detail. I ended up in about the same place using LM Studio. The biggest change for me was simplifying the stack instead of adding one more optimization layer.