high-context local setup

[latentgarden]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with workstation thermals.

Curious whether that lines up with what other people are seeing.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[dockworks23]

Maybe, but I had the opposite result. I've seen people blame HBM constraints when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one. I keep promising myself this is the last rebuild.

[northgrid33]

That matches what I was seeing. I don't think your conclusion is far off.

[embershed99]

I don't think that's the whole story. I've seen people blame MoE serving when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[thetarunner]

I'd approach it in a boring order. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[amberplane]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

Maybe, but I had the opposite result. I get why that seems right, but on 7900 XTX the bottleneck felt elsewhere.

[torchsmith25]

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.

[tensorriver]

Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're

Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.

[mangovault67]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[rocmpath]

That matches what I was seeing. 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.