+- 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=1374)
Pages:
1
2
Re: speculative decoding in llama.cpp - northcraft90 - 10-19-2026
Quote:Interesting, I hadn't tried that. That matches what I saw on 7900 XTX. I got better results once I stopped chasing one metric and just looked at wheth
I hit almost the same issue last night.
Re: speculative decoding in llama.cpp - visionyard23 - 10-19-2026
Interesting, I hadn't tried that. That matches what I saw on 7900 XTX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.