10-09-2026, 07:04 PM
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.
|
speculative decoding in llama.cpp
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
speculative decoding in llama.cpp - by embershed99 - 10-07-2026, 01:45 AM
Re: speculative decoding in llama.cpp - by mangotinker73 - 10-09-2026, 02:08 AM
Re: speculative decoding in llama.cpp - by vrambandit - 10-09-2026, 10:48 AM
Re: speculative decoding in llama.cpp - by marbletrack - 10-09-2026, 07:04 PM
Re: speculative decoding in llama.cpp - by northcraft90 - 10-09-2026, 09:46 PM
Re: speculative decoding in llama.cpp - by vrambandit - 10-09-2026, 10:45 PM
Re: speculative decoding in llama.cpp - by visionyard23 - 10-10-2026, 01:23 AM
Re: speculative decoding in llama.cpp - by vrambandit - 10-10-2026, 02:52 AM
Re: speculative decoding in llama.cpp - by papermixer4 - 10-10-2026, 03:22 PM
Re: speculative decoding in llama.cpp - by sanepeak48 - 10-10-2026, 03:39 PM
Re: speculative decoding in llama.cpp - by macroforge - 10-11-2026, 04:18 PM
Re: speculative decoding in llama.cpp - by mangotinker73 - 10-12-2026, 12:59 AM
|
Users browsing this thread: 1 Guest(s)