speculative decoding in llama.cpp

speculative decoding in llama.cpp - Printable Version

+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: llama.cpp / GGUF (https://www.datasculpting.ai/inference/forumdisplay.php?fid=35)
+--- Thread: speculative decoding in llama.cpp (/showthread.php?tid=693)

Pages: 1 2

Re: speculative decoding in llama.cpp - visionyard23 - 10-07-2026

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.

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

Re: speculative decoding in llama.cpp - macroforge - 10-08-2026

I'd start with the simpler stack.

Re: speculative decoding in llama.cpp - visionforge - 10-09-2026

What worked for me was pretty simple. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.