]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 53e4db1)
gguf-py: enable reading non-native endian files (#12081)
authorAleksei Nikiforov <redacted>
Wed, 26 Feb 2025 11:39:27 +0000 (12:39 +0100)
committerGitHub <redacted>
Wed, 26 Feb 2025 11:39:27 +0000 (11:39 +0000)
commit3567ee3a94d57ba72b6d023ca507d11e75767edb
treed2a2a4b574988982998373a665bcbd22496b116ftree
parent53e4db10126e277486eccb94c6728f4146c75741commit | diff
gguf-py: enable reading non-native endian files (#12081)

Currently self.byte_order is never used.
Actually use it to byteswap read data to
allow reading big endian files on little endian systems
and vice versa.

Now it's possible to convert little-endian model
into a big-endian model and back
on a little-endian system.
gguf-py/gguf/gguf_reader.py diff | blob | history
Packaging of ggml-org/llama.cpp