]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b80cf3b)
gguf-split: split and merge gguf per batch of tensors (#6135)
authorPierrick Hymbert <redacted>
Tue, 19 Mar 2024 11:05:44 +0000 (12:05 +0100)
committerGitHub <redacted>
Tue, 19 Mar 2024 11:05:44 +0000 (12:05 +0100)
commitd0d5de42e5a65865b5fddb6f5c785083539b74c3
tree06e1d97ac44314f39c1b40358c2838b46bed71d9tree
parentb80cf3b2d1dee0ad325f7a794fecc66befce7336commit | diff
gguf-split: split and merge gguf per batch of tensors (#6135)

* gguf-split: split and merge gguf files per tensor

* gguf-split: build with make toolchain

* gguf-split: rename `--split-tensors-size` to `--split-max-tensors`. Set general.split_count KV to all split

* split : minor style + fix compile warnings

* gguf-split: remove --upload not implemented

---------

Co-authored-by: Georgi Gerganov <redacted>
Makefile diff | blob | history
examples/CMakeLists.txt diff | blob | history
examples/gguf-split/CMakeLists.txt [new file with mode: 0644] blob
examples/gguf-split/README.md [new file with mode: 0644] blob
examples/gguf-split/gguf-split.cpp [new file with mode: 0644] blob
Packaging of ggml-org/llama.cpp