+- 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=951)
Pages:
1
2
Re: speculative decoding in llama.cpp - quantsupply - 10-14-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly.
Re: speculative decoding in llama.cpp - thetagrid15 - 10-15-2026
What worked for me was pretty simple. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: speculative decoding in llama.cpp - phasescope - 10-15-2026
I think the bottleneck is somewhere else. I've seen people blame tool calling when the real issue was much more mundane.
Re: speculative decoding in llama.cpp - quietarch - 10-15-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.
Re: speculative decoding in llama.cpp - northcraft90 - 10-15-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.