workflow automation with local models on dual 3090

[northgrid33]

Did a bit of testing and thought I'd post the result here.

Short version: vLLM behaved well for me, but only after I stopped ignoring VRAM headroom.

Curious if anyone else landed in the same place.

[phasestream53]

Did a bit of testing and thought I'd post the result here.

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[northgrid33]

Did a bit of testing and thought I'd post the result here.

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

[southden]

A couple things I'd check first. 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.

[labline]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. A lot of these threads end

A couple things I'd check first. If you're on MLX, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.

[mintstation99]

I'd approach it in a boring order. 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.

[ggufvault]

I tested this tonight. On M3 Max with vLLM, I saw basically the same behavior. I expected the model choice to matter more than it did.

[llm_wren]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

[bytegarden73]

Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[thetanest]

Not sure I agree there. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere.