]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml : quantization refactoring (#3833)
authorGeorgi Gerganov <redacted>
Sun, 29 Oct 2023 16:32:28 +0000 (18:32 +0200)
committerGitHub <redacted>
Sun, 29 Oct 2023 16:32:28 +0000 (18:32 +0200)
commitd69d777c02b9ac405a95f3cbfba219a990caefff
tree89c43e860850c0647b41025442e61ffa8534c5d7
parentff3bad83e29e3009010cbc923bebd769055eaa7f
ggml : quantization refactoring (#3833)

* ggml : factor all quantization code in ggml-quants

ggml-ci

* ggml-quants : fix Zig and Swift builds + quantize tool

ggml-ci

* quantize : --pure option for disabling k-quant mixtures

---------

Co-authored-by: cebtenzzre <redacted>
13 files changed:
CMakeLists.txt
Makefile
Package.swift
build.zig
examples/quantize/quantize.cpp
ggml-quants.c [new file with mode: 0644]
ggml-quants.h [new file with mode: 0644]
ggml.c
ggml.h
k_quants.c [deleted file]
k_quants.h [deleted file]
llama.cpp
llama.h