]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Fixed save_imatrix to match old behaviour for MoE (#7099)
authorjukofyork <redacted>
Wed, 8 May 2024 00:24:16 +0000 (01:24 +0100)
committerGitHub <redacted>
Wed, 8 May 2024 00:24:16 +0000 (02:24 +0200)
commit48b2f9c1fc71ab7df5432be2ed9fa7cdf5e8405e
tree1b5458baebd1f6fb239ac01df636f7ee9123494d
parentaf0a5b616359809ce886ea433acedebb39b12969
Fixed save_imatrix to match old behaviour for MoE (#7099)

* Fixed save_imatrix to match old behaviour for MoE

This fix is simple and clear, but unnecessarily doubles the memory overhead..

* Fixed missing idx variable

* Unconditionally increment ncall

Co-authored-by: slaren <redacted>
* Fixed 2 bugs in save_imatrix()

- Fixed segfault bug because the counts vector needed to be created.
- Fixed pre-existing bug didn't actually add to the counts for "--combine" option.

* ncall needs summing too

* Trailing whitespace

---------

Co-authored-by: slaren <redacted>
examples/imatrix/imatrix.cpp