+- 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=834)
Pages:
1
2
speculative decoding in llama.cpp - embershed99 - 10-07-2026
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around PyTorch and 7900 XTX.
I'm especially interested in mistakes worth avoiding.
Re: speculative decoding in llama.cpp - mangotinker73 - 10-09-2026
A couple questions before I guess too hard. Is this local-only or are you routing anything externally?
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: speculative decoding in llama.cpp - vrambandit - 10-09-2026
Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: speculative decoding in llama.cpp - marbletrack - 10-09-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: speculative decoding in llama.cpp - northcraft90 - 10-09-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: speculative decoding in llama.cpp - vrambandit - 10-09-2026
A couple questions before I guess too hard. Are you testing this on Threadripper box or something else?
Re: speculative decoding in llama.cpp - visionyard23 - 10-10-2026
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 - vrambandit - 10-10-2026
following this because I'm in the same boat.
Re: speculative decoding in llama.cpp - papermixer4 - 10-10-2026
My first guess would be this: If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: speculative decoding in llama.cpp - sanepeak48 - 10-10-2026
A couple things I'd check first. If you're on SGLang, 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.