]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 0c89864)
model-conversion : add device option to embd run orig model (#18386)
authorDaniel Bevenius <redacted>
Mon, 29 Dec 2025 12:37:02 +0000 (13:37 +0100)
committerGitHub <redacted>
Mon, 29 Dec 2025 12:37:02 +0000 (13:37 +0100)
commit7cbec34a6308592b2a633535493842144d345d14
tree1d4ce9290c82688550b9ca3f44842f09360e29b1tree
parent0c8986403b52f43e4d3bf519afd78aefcdaee238commit | diff
model-conversion : add device option to embd run orig model (#18386)

This commit refactors the original model embedding script to include a
device selection option. Users can now specify the device (cpu, cuda,
mps, auto) via command-line arguments. It also refactors the code to be
more structured.
examples/model-conversion/scripts/embedding/run-original-model.py diff | blob | history
Packaging of ggml-org/llama.cpp