+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Security, Privacy & Safety (https://www.datasculpting.ai/inference/forumdisplay.php?fid=23)
+--- Forum: Model / Agent Security (https://www.datasculpting.ai/inference/forumdisplay.php?fid=77)
+--- Thread: sandboxing agent actions: what are you seeing? (/showthread.php?tid=1363)
sandboxing agent actions: what are you seeing? - quantshed - 10-16-2026
Has anyone else run into this?
My current setup is TensorRT-LLM with A6000, and I keep running into prefix caching.
Not looking for the perfect answer, mostly what worked in real use. Turns out 'just one more test' was a lie.
Re: sandboxing agent actions: what are you seeing? - quiettoken - 10-18-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at consumer GPUs. Once you know the plain path works, then add the faster path back in piece by piece.
Re: sandboxing agent actions: what are you seeing? - prompttinker44 - 10-18-2026
Quote:A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. A lot of these threads end u
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: sandboxing agent actions: what are you seeing? - routecraft - 10-18-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: sandboxing agent actions: what are you seeing? - dockember - 10-18-2026
Thanks, that helps. I don't think your conclusion is far off.
Re: sandboxing agent actions: what are you seeing? - plainember52 - 10-18-2026
that fixed it for me too.
Re: sandboxing agent actions: what are you seeing? - rasterbench - 10-19-2026
subscribed, curious where this lands.
Re: sandboxing agent actions: what are you seeing? - latentcraft - 10-19-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
I'm happy to test one more variant if you want a second data point.
Re: sandboxing agent actions: what are you seeing? - torchsmith25 - 10-19-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?