ik_llama.cpp/ggml-alloc.c at 1004b730b1e46b793139add160573b26d99488f4 - ik_llama.cpp - Public git mirror

ikawrakow/ik_llama.cpp

mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 02:41:47 +00:00

Files

slaren ab0c5dbd6d llama : pre-allocate input tensors in a separate buffer (#5100 )

2024-01-24 12:48:14 +01:00

29 KiB

Raw Blame History

View Raw