]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 6e08281)
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)
authorGeorgi Gerganov <redacted>
Mon, 30 Oct 2023 17:19:15 +0000 (19:19 +0200)
committerGitHub <redacted>
Mon, 30 Oct 2023 17:19:15 +0000 (19:19 +0200)
commit207b51900e15cc7f89763a3bb1c565fe11cbb45d
tree0e37b11eafe495bfc66893f70e1e471bf52c3cd4tree
parent6e08281e588bbba1a5d180290a94a43f167f3a1acommit | diff
ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)

* ggml : move FP16 <-> FP32 stuff to ggml-impl.h

ggml-ci

* tests : fix ARM build

* ggml : explicitly initialize deprecated type traits

* ggml : add math.h to ggml-impl.h

* ggml : remove duplicate static assert macros

* ggml : prefix lookup tables with ggml_

ggml-ci

* ggml-impl : move extern "C" to start of file
ggml-impl.h [new file with mode: 0644] blob
ggml-quants.c diff | blob | history
ggml-quants.h diff | blob | history
ggml.c diff | blob | history
llama.cpp diff | blob | history
tests/test-double-float.cpp diff | blob | history
tests/test-quantize-fns.cpp diff | blob | history
Packaging of ggml-org/llama.cpp