Embeddings discussion

[rasterhall]

I'd approach it in a boring order. If you're on Ollama, 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.

[ggufwire22]

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

[paperport64]

My first guess would be this: If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.