]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220)
authorGeorgi Gerganov <redacted>
Thu, 25 Sep 2025 08:30:16 +0000 (11:30 +0300)
committerGitHub <redacted>
Thu, 25 Sep 2025 08:30:16 +0000 (11:30 +0300)
commitdfcd53f7ecb9bb897a9d752d09c59d10be47237a
tree5799b5934269c50a206753f9a4fd6409ef96440e
parent4ea00794b8c995b6deaf4bac159c1778dc27419a
metal : fuse NORM + MUL + ADD, support non-multiples of 4 (#16220)

* metal : fuse NORM + MUL + ADD

* metal : support norms of non-multiple of 4

* cont : fix comment [no ci]
ggml/src/ggml-metal/ggml-metal-common.cpp
ggml/src/ggml-metal/ggml-metal-device.cpp
ggml/src/ggml-metal/ggml-metal-device.h
ggml/src/ggml-metal/ggml-metal-device.m
ggml/src/ggml-metal/ggml-metal-impl.h
ggml/src/ggml-metal/ggml-metal-ops.cpp
ggml/src/ggml-metal/ggml-metal-ops.h
ggml/src/ggml-metal/ggml-metal.metal
tests/test-backend-ops.cpp