driver/framework news roundup

[nanogarden]

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

The more I work with local setups, the more it seems like reranking decides everything downstream.

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

[audiopoint18]

Not sure I agree there. I've seen people blame tail latency when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[phaseshed]

Appreciate the detail. I don't think your conclusion is far off.

[nanogarden]

Good point. That matches what I saw on dual 3090.

[mangowire]

I'd approach it in a boring order. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[audiopoint18]

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. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[amberrunner]

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. A lot

I'd approach it in a boring order. On B200, 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.

If you post your exact settings, people here can probably narrow it down pretty fast.

[fastlab]

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

[mangowire]

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

[nanogarden]

Interesting, I hadn't tried that. I ended up in about the same place using Ollama.