]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml : remove old quantization functions (#5942)
authorGeorgi Gerganov <redacted>
Sat, 9 Mar 2024 13:53:59 +0000 (15:53 +0200)
committerGitHub <redacted>
Sat, 9 Mar 2024 13:53:59 +0000 (15:53 +0200)
commit5b09797321430f08caf0473143a962916ab2ea89
treeb6077558c8b25bbe073736c0f13c6ef169842300
parent97c09585d65a95864773b4d25d66d0f708baf38d
ggml : remove old quantization functions (#5942)

* ggml : remove old quantization functions

ggml-ci

* ggml : simplify ggml_quantize_chunk

ggml-ci

* ggml : restrict correctness

ggml-ci

* ggml : remove hist data from the quantization API

ggml-ci

* tests : remove hist usage in test-backend-ops

ggml-ci

* vulkan : remove hist and fix typo
examples/benchmark/benchmark-matmult.cpp
examples/llava/clip.cpp
ggml-quants.c
ggml-quants.h
ggml-vulkan.cpp
ggml.c
ggml.h
llama.cpp
tests/test-backend-ops.cpp