industry move that matters for local users for Llama

[audiopoint18]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about prefill/decode split.

Would rather learn from your scars than collect my own all at once.

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

[routearch]

A couple things I'd check first. On A6000, 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.

[vrampilot]

A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glam

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[bytelab]

That matches what I was seeing. The pattern around VRAM headroom has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[mangohouse]

Need a little more detail here. Is this local-only or are you routing anything externally?

[southpatch]

I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Not glamorous advice, but repeatable baselines save a lot of time.

[southpatch]

Good point. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[amberrunner]

What worked for me was pretty simple. On 5090, 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.

[bytestack]

same here on my side.

[dockriver]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.