]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama: introduce support for model-embedded sampling parameters (#17120)
authorAaron Teo <redacted>
Tue, 25 Nov 2025 01:56:07 +0000 (09:56 +0800)
committerGitHub <redacted>
Tue, 25 Nov 2025 01:56:07 +0000 (09:56 +0800)
commit877566d512d02a3a288ea38c1f7b1c25ccd6c082
treeebd5ba9a4f98ce04569be92fa4457de3d909ae69
parent3d07caa99bff9213411202b4063aa2f44e919654
llama: introduce support for model-embedded sampling parameters (#17120)
common/arg.cpp
common/common.cpp
common/common.h
gguf-py/gguf/constants.py
gguf-py/gguf/gguf_writer.py
gguf-py/gguf/metadata.py
include/llama.h
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp