]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: cb1adf8)
convert : handle compressed-tensors quant method (#17069)
authorcompilade <redacted>
Sun, 9 Nov 2025 14:45:50 +0000 (09:45 -0500)
committerGitHub <redacted>
Sun, 9 Nov 2025 14:45:50 +0000 (09:45 -0500)
commit1c07c0c68c692d39b83f491bad9447af852bb652
tree5da5a262e0ff4e266b1865cb0c1ed0e6891e8ab7tree
parentcb1adf885105da7ce23db746b4202f4e987aa3e8commit | diff
convert : handle compressed-tensors quant method (#17069)

* convert : handle compressed-tensors quant method

* convert : handle int-quantized models

* convert : handle naive-quantized models

* gguf-py : __pos__ is also unary

* convert : fix flake8 lint

* convert : use F32 for dequant of pack-quantized tensors
convert_hf_to_gguf.py diff | blob | history
gguf-py/gguf/lazy.py diff | blob | history
Packaging of ggml-org/llama.cpp