speculative decoding in llama.cpp: anyone testing this?

[northcraft90]

Appreciate the detail. I ended up in about the same place using Ollama. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[vrambandit]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[griffinloom66]

Interesting, I hadn't tried that. The pattern around MoE serving has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[northcraft90]

Interesting, I hadn't tried that. The pattern around MoE serving has been pretty similar for me. The biggest change for me was simplifying the stack i

That matches what I was seeing. The pattern around tail latency has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.