09-27-2026, 08:28 PM
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.
|
prefix caching in llama.cpp with MLX
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
prefix caching in llama.cpp with MLX - by thetagrid15 - 09-22-2026, 11:23 PM
Re: prefix caching in llama.cpp with MLX - by embershed99 - 09-23-2026, 02:05 AM
Re: prefix caching in llama.cpp with MLX - by dockridge - 09-23-2026, 02:47 AM
Re: prefix caching in llama.cpp with MLX - by bytesupply76 - 09-27-2026, 08:44 PM
Re: prefix caching in llama.cpp with MLX - by thetagrid15 - 09-23-2026, 04:29 AM
Re: prefix caching in llama.cpp with MLX - by vectorport - 09-26-2026, 04:31 AM
Re: prefix caching in llama.cpp with MLX - by vrambandit - 09-26-2026, 07:18 AM
Re: prefix caching in llama.cpp with MLX - by kernelmike - 09-26-2026, 07:18 PM
Re: prefix caching in llama.cpp with MLX - by macroforge - 09-26-2026, 08:07 PM
Re: prefix caching in llama.cpp with MLX - by dockridge - 09-27-2026, 08:28 PM
Re: prefix caching in llama.cpp with MLX - by dockridge - 09-27-2026, 11:35 PM
|
Users browsing this thread: 1 Guest(s)