+- 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: anyone testing this? (/showthread.php?tid=534)
Pages:
1
2
Re: speculative decoding in llama.cpp: anyone testing this? - northcraft90 - 10-05-2026
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.
Re: speculative decoding in llama.cpp: anyone testing this? - vrambandit - 10-08-2026
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.
Re: speculative decoding in llama.cpp: anyone testing this? - griffinloom66 - 10-08-2026
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.
Re: speculative decoding in llama.cpp: anyone testing this? - northcraft90 - 10-08-2026
Quote: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.