ggml : Q2k interleaving implementation - x86/x64 SIMD (#14373)

Browse Source

* Initial Q2_K Block Interleaving Implementation

* Addressed review comments and clean up of the code

* Post rebase fixes

* Initial CI/CD fixes

* Update declarations in arch-fallback.h

* Changes for GEMV Q2_K in arch-fallback.h

* Enable repacking only on AVX-512 machines

* Update comments in repack.cpp

* Address q2k comments

---------

Co-authored-by: Manogna-Sree <elisetti.manognasree@multicorewareinc.com>

...

This commit is contained in:

Srihari-mcw

2025-08-01 11:50:33 +05:30

committed by GitHub

parent ba42794c9e

commit baad94885d

4 changed files with 3484 additions and 0 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

3196

ggml/src/ggml-cpu/arch/x86/repack.cpp

File diff suppressed because it is too large Load Diff