how much orchestration is too much

[llm_wren]

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

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around llama.cpp and 4090.

I'm especially interested in mistakes worth avoiding.

This is mostly for local work rather than public serving.

[torchshed]

What worked for me was pretty simple. If you're on Ollama, 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.

[llm_wren]

that fixed it for me too. At this point the real bottleneck is my patience.

[mintforge]

A couple things I'd check first. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[llm_wren]

My first guess would be this: On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[labline]

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

[ggufvault]

following this because I'm in the same boat.

[thetanest]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[llm_wren]

My first guess would be this: On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[phasestream53]

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