long context that stayed useful for Llama

[emberquill]

Curious what people here are seeing.

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling tail latency.

Would appreciate practical advice rather than theory.

[syshouse]

My first guess would be this: On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[sanescope]

My first guess would be this: On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

Good point. I ended up in about the same place using Ollama. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[bytesupply76]

I tested this tonight. On 5090 with MLX, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.

[torchkite]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[cozywire]

Thanks, that helps. That matches what I saw on B200.

[quantyard]

My first guess would be this: If you're on SGLang, 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.

[quiethouse]

A couple things I'd check first. On mini PC, 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.

[audiopoint18]

Maybe, but I had the opposite result. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[tinycontext]

following this because I'm in the same boat.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.