speculative decoding actually worth it for Qwen

[tinycontext]

A couple things I'd check first. If you're on Ollama, 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.

I'm happy to test one more variant if you want a second data point.

[cacheline]

Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[vectorfield]

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

[cacheline]

Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimi

Appreciate the detail. That matches what I saw on GB200. The biggest change for me was simplifying the stack instead of adding one more optimization layer.