]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 732b5fb)
ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture...
authorSrihari-mcw <redacted>
Thu, 20 Mar 2025 11:35:34 +0000 (17:05 +0530)
committerGitHub <redacted>
Thu, 20 Mar 2025 11:35:34 +0000 (13:35 +0200)
commit3d82dbcbce2c677fc35fbf99574ccd107d95a1f8
tree72b931acb56e018a7f445150c1818616eadabe7btree
parent732b5fbf5e7f9cf069942f0c5850ee959ef321bacommit | diff
ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture (#12332)

* Add block interleaving support for Q4_K quantization

* Remove whitespaces and fix CI/CD issues

* Update pointer of bsums from int16_t to const int16_t

* Add vector version of quantize_q8_K_4x8 function

* Update code formatting based on review comments
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp diff | blob | history
Packaging of ggml-org/llama.cpp