]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : refactor model loader with backend registry (#10026)
authorDiego Devesa <redacted>
Wed, 30 Oct 2024 01:01:23 +0000 (02:01 +0100)
committerGitHub <redacted>
Wed, 30 Oct 2024 01:01:23 +0000 (02:01 +0100)
commitc5b0f4b5d90297f3e729fca7f78ddb25fcab5ddc
tree23cdc7a7feced7b52fec13646cc64c02575a6f3d
parent8f275a7c4593aa34147595a90282cf950a853690
llama : refactor model loader with backend registry (#10026)
18 files changed:
examples/llama-bench/llama-bench.cpp
ggml/include/ggml-backend.h
ggml/include/ggml-cuda.h
ggml/src/ggml-amx.cpp
ggml/src/ggml-backend-impl.h
ggml/src/ggml-backend.cpp
ggml/src/ggml-blas.cpp
ggml/src/ggml-cann.cpp
ggml/src/ggml-cuda.cu
ggml/src/ggml-kompute.cpp
ggml/src/ggml-metal.m
ggml/src/ggml-rpc.cpp
ggml/src/ggml-sycl.cpp
ggml/src/ggml-vulkan.cpp
ggml/src/ggml.c
include/llama.h
scripts/compare-llama-bench.py
src/llama.cpp