]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama-quant : fail early on missing imatrix, refactor type selection, code cleanup...
authorddh0 <redacted>
Tue, 10 Mar 2026 06:16:05 +0000 (01:16 -0500)
committerGitHub <redacted>
Tue, 10 Mar 2026 06:16:05 +0000 (08:16 +0200)
commit1dab5f5a443a7b972005c56fb92eca2b07d57fea
treedd05b63b001e8f10c868af3daaac31ae3a374684
parentc96f608d9861f7e8466bc1b6ac2ff4e3c6f96641
llama-quant : fail early on missing imatrix, refactor type selection, code cleanup (#19770)

* quantize : imatrix-fail early + code cleanup

* fix manual override printing

it's in the preliminary loop now, so needs to be on its own line

* revert header changes per ggerganov

* remove old #includes

* clarify naming

rename `tensor_quantization` to `tensor_typo_option` to descirbe its
functionality

* fix per barto
src/llama-quant.cpp
tools/quantize/quantize.cpp