+- 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=1458)
Pages:
1
2
Re: speculative decoding in llama.cpp: anyone testing this? - bytesupply76 - 10-19-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints. Not glamorous advice, but repeatable baselines save a lot of time.
Re: speculative decoding in llama.cpp: anyone testing this? - stackpilot - 10-19-2026
What worked for me was pretty simple. If you're on vLLM, 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? - embershed99 - 10-19-2026
I'd approach it in a boring order. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Re: speculative decoding in llama.cpp: anyone testing this? - visionyard23 - 10-19-2026
Quote:I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints. Not gla
Ran a quick check on my box. On M3 Max with vLLM, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.
Re: speculative decoding in llama.cpp: anyone testing this? - northquill - 10-19-2026
Good point. That matches what I saw on dual 3090. 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? - bytesupply76 - 10-19-2026
I hit almost the same issue last night.