+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Security, Privacy & Safety (https://www.datasculpting.ai/inference/forumdisplay.php?fid=23)
+--- Forum: Sandboxing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=78)
+--- Thread: containment for model-driven automation (/showthread.php?tid=261)
Pages:
1
2
containment for model-driven automation - cudapoint - 09-13-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: llama.cpp on Threadripper box, keeping MoE serving in mind from the start.
If someone wants the exact settings I can clean them up and post them.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: containment for model-driven automation - rocmriley - 09-13-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
Interesting, I hadn't tried that. The pattern around embeddings 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: containment for model-driven automation - phaseshed - 09-14-2026
I'd start with the simpler stack.
Re: containment for model-driven automation - thetafield - 09-14-2026
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: containment for model-driven automation - rocmstack25 - 09-14-2026
A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: containment for model-driven automation - thetaarch43 - 09-14-2026
What worked for me was pretty simple. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: containment for model-driven automation - mangopeak72 - 09-15-2026
Quote:What worked for me was pretty simple. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
A couple things I'd check first. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: containment for model-driven automation - torchdesk - 09-15-2026
Need a little more detail here. Is this local-only or are you routing anything externally?
Re: containment for model-driven automation - cobaltspark - 09-15-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: containment for model-driven automation - dockember - 09-15-2026
following this because I'm in the same boat.