]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 184215e)
ggml : reuse quantum structs across backends (#5943)
authorGeorgi Gerganov <redacted>
Tue, 12 Mar 2024 12:27:20 +0000 (14:27 +0200)
committerGitHub <redacted>
Tue, 12 Mar 2024 12:27:20 +0000 (14:27 +0200)
commit8030da7afea2d89f997aeadbd14183d399a017b9
treedf7905572642780ca4e185f29ba14624918c29fatree
parent184215e783dfad76aded2c68244c327a5c507df5commit | diff
ggml : reuse quantum structs across backends (#5943)

* ggml : reuse quant blocks across backends

ggml-ci

* ggml : define helper constants only for CUDA and SYCL

ggml-ci

* ggml : define helper quantum constants for SYCL

ggml-ci
ggml-common.h diff | blob | history
ggml-cuda.cu diff | blob | history
ggml-metal.m diff | blob | history
ggml-metal.metal diff | blob | history
ggml-quants.c diff | blob | history
ggml-quants.h diff | blob | history
ggml-sycl.cpp diff | blob | history
Packaging of ggml-org/llama.cpp