llama.cpp/ggml/src/ggml-alloc.c at c2a67efe38e6782c0217e1de3edc68de6951612b - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-20 12:07:33 +00:00

Files

Jeff Bolz 1b598b3058 vulkan: use smaller combined allocations to avoid fragmentation (#11551 )

2025-02-06 07:02:18 +01:00

37 KiB

Raw Blame History

View Raw