llama.cpp/include/llama.h at 16bcc1259d311d0fd37fe00fefcc7900324d38cb

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-10 10:27:03 +00:00

Files

Georgi Gerganov 16bcc1259d kv-cache : pad the cache size to 256 for performance (#17046 )

* kv-cache : pad the size of the small SWA cache for performance

* context : pad the total context to 256

* cont : future-proof the swa pad

* server : adjust test params to new logic

2025-11-07 20:03:25 +02:00

71 KiB

Raw Blame History

View Raw

71 KiB Raw Blame History

71 KiB

Raw Blame History