long context that stayed useful

[torchstation]

Thought I'd post a small recipe because a lot of threads ask similar things.

Just sharing a setup that ended up working reasonably well: Kimi, llama.cpp, A6000, with a lot of attention on router policy.

Feel free to tear it apart if you see something dumb.

The part that surprised me was how much the boring details mattered more than the model choice.

[torchstation]

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

[tensorriver]

That matches what I was seeing. That matches what I saw on B200. The logs were somehow calmer than I was.

[routecraft]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at small local stacks. Once you know the plain path works, then add the faster path back in piece by piece.

[quiethouse]

Good point. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[ggufvault]

What worked for me was pretty simple. On 4090, 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.

[torchkite]

A couple things I'd check first. If you're on vLLM, 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.

[turboscope5]

Interesting, I hadn't tried that. The pattern around small local stacks 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.