]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
overview / pkg / ggml / sources / ggml / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 58698ab)
ggml : Q2k interleaving implementation - x86/x64 SIMD (llama/14373)
authorSrihari-mcw <redacted>
Fri, 1 Aug 2025 06:20:33 +0000 (11:50 +0530)
committerGeorgi Gerganov <redacted>
Sat, 2 Aug 2025 14:51:21 +0000 (17:51 +0300)
commit311c47b434f47609af863ae93c70bc680acdad05
tree0d3bf2d5c90a4f70fe2f98c958498c9291988479tree
parent58698ab103df4ac8a9def01fbd37c4a371bff7e5commit | diff
ggml : Q2k interleaving implementation - x86/x64 SIMD (llama/14373)

* 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 <redacted>
src/ggml-cpu/arch-fallback.h diff | blob | history
src/ggml-cpu/arch/x86/repack.cpp diff | blob | history
src/ggml-cpu/repack.cpp diff | blob | history
src/ggml-cpu/repack.h diff | blob | history
Packaging of ggml-org/ggml