containment for model-driven automation

[vramport]

I figured I'd ask here before changing everything.

I'm mostly working with DeepSeek in llama.cpp on B200. The part I'm trying to understand is NVFP4.

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.

[phasescope]

What exact setup are you running? Are you testing this on M3 Max or something else?

Appreciate the detail. I ended up in about the same place using MLX.

[vrambandit]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time. The logs were somehow calmer than I was.

[tinycontext]

Appreciate the detail. The pattern around router policy has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[kernelgrid]

subscribed, curious where this lands.

[llmtrack26]

subscribed, curious where this lands.

that fixed it for me too.

[rasterpoint]

subscribed, curious where this lands.

Need a little more detail here. Are you testing this on dual 3090 or something else?

I'm happy to test one more variant if you want a second data point. I keep promising myself this is the last rebuild.

[cozykite]

What exact setup are you running? Are you testing this on M3 Max or something else?

I'm happy to test one more variant if you want a second data point.