mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-04 09:32:00 +00:00
85a7d8677b
* memory : remove KV cache size padding * cont : restore padding for n_kv tensor shape * server : use slot context size instead of training context size * server : simplify context limit logic
3.0 KiB
3.0 KiB