Introduce support for GGJT v3 file format

Browse source

llama.com can now load weights that use the new file format which was
introduced a few weeks ago. Note that, unlike llama.cpp, we will keep
support for old file formats in our tool so you don't need to convert
your weights when the upstream project makes breaking changes. Please
note that using ggjt v3 does make avx2 inference go 5% faster for me.

...

This commit is contained in:

Justine Tunney 2023-06-03 13:48:52 -07:00

parent 6ae18a10ba

commit 8fdb31681a

No known key found for this signature in database

GPG key ID: BE714B4575D6E328

33 changed files with 3829 additions and 371 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

1200

third_party/ggml/ggml.c vendored

View file

File diff suppressed because it is too large Load diff