routing between local and hosted with vLLM

[vectorshed43]

Thanks, that helps. That matches what I saw on M3 Max. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[torchstation]

Thanks, that helps. That matches what I saw on M3 Max. I got better results once I stopped chasing one metric and just looked at whether the workflow

My first guess would be this: 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.

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

[llmtrack]

Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[relaynest82]

Thanks, that helps. The pattern around speculative decoding 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.