]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: ec6c742)
quantize: add option --tensor-type-file to llama-quantize (#18572)
authorEugeoSynthesisThirtyTwo <redacted>
Sat, 31 Jan 2026 03:39:21 +0000 (04:39 +0100)
committerGitHub <redacted>
Sat, 31 Jan 2026 03:39:21 +0000 (11:39 +0800)
commit3dd95914d09b155eed84664b9abdbbffae238738
tree5c9851ea7ea3da86bcdc0f8fd0ff729c3ef55642tree
parentec6c7421e4f3c0e1bdb9fdc6ee9670e14a490854commit | diff
quantize: add option --tensor-type-file to llama-quantize (#18572)

* add option --tensor-type-file to llama-quantize, but it raises an error.

* add error message when file not found

* quantize: update help menu, fix CI

Signed-off-by: Aaron Teo <redacted>
---------

Signed-off-by: Aaron Teo <redacted>
Co-authored-by: Your Name <redacted>
Co-authored-by: Aaron Teo <redacted>
tools/quantize/quantize.cpp diff | blob | history
Packaging of ggml-org/llama.cpp