10-19-2026, 02:09 AM
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
|
speculative decoding in llama.cpp
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
speculative decoding in llama.cpp - by phasetrack - 10-16-2026, 10:05 PM
Re: speculative decoding in llama.cpp - by bytesupply76 - 10-16-2026, 11:11 PM
Re: speculative decoding in llama.cpp - by thetagrid15 - 10-18-2026, 11:38 AM
Re: speculative decoding in llama.cpp - by mellowwire98 - 10-18-2026, 12:08 PM
Re: speculative decoding in llama.cpp - by cozykite - 10-18-2026, 08:09 PM
Re: speculative decoding in llama.cpp - by dockridge - 10-18-2026, 09:13 PM
Re: speculative decoding in llama.cpp - by embershed99 - 10-18-2026, 09:34 PM
Re: speculative decoding in llama.cpp - by macroforge - 10-19-2026, 12:57 AM
Re: speculative decoding in llama.cpp - by latentcraft - 10-19-2026, 02:09 AM
Re: speculative decoding in llama.cpp - by mangotinker73 - 10-19-2026, 02:43 AM
Re: speculative decoding in llama.cpp - by northcraft90 - 10-19-2026, 03:21 AM
Re: speculative decoding in llama.cpp - by visionyard23 - 10-19-2026, 05:20 AM
|
Users browsing this thread: 1 Guest(s)