llama.cpp/ggml-alloc.c at 5f1925a8cef81eb9b372faaae34b0dd76d5361d4 - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00

Files

slaren 1387ea2117 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