+- 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=385)
Pages:
1
2
Re: speculative decoding in llama.cpp - vrambandit - 09-30-2026
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.
Re: speculative decoding in llama.cpp - northcraft90 - 09-30-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, 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.
Re: speculative decoding in llama.cpp - vrambandit - 10-01-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
Re: speculative decoding in llama.cpp - thetagrid15 - 10-01-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: speculative decoding in llama.cpp - bytegarden73 - 10-01-2026
Quote:My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. A lot of these threads end
Good point. 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.
Re: speculative decoding in llama.cpp - dockridge - 10-02-2026
Quote:[quote]My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. A lot of these threa
Not sure I agree there. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. I keep promising myself this is the last rebuild.