Help with Embeddings

[torchdesk]

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

After a few runs on mini PC, I ended up with decent performance, but the setup only really made sense once I adjusted around tail latency.

Nothing scientific here, just practical notes from a real setup.

This is mostly for local work rather than public serving.

[vectorshed43]

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

[vramscope]

What exact setup are you running? Is this local-only or are you routing anything externally?

[rasterhall]

What exact setup are you running? Is this local-only or are you routing anything externally?

Tried to reproduce it just now. On A6000 with MLX, I saw basically the same behavior. I expected the model choice to matter more than it did.

[vramscope]

following this because I'm in the same boat.

[edgecoast]

Interesting, I hadn't tried that. 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.

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

[rasterhall]

Thanks, that helps. 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.

[quantnest]

My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

[ggufwire22]

Thanks, that helps. I ended up in about the same place using SGLang. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[paperport64]

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.