]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : add option to override model tensor buffers (#11397) upstream/0.0.5028
authorDiego Devesa <redacted>
Wed, 2 Apr 2025 12:52:01 +0000 (14:52 +0200)
committerGitHub <redacted>
Wed, 2 Apr 2025 12:52:01 +0000 (14:52 +0200)
commite0e912f49b3195ef9d0c51378629ba03c9b972da
treea3f99677005a06619f95ddb4faa98f5fabb70915
parenta10b36c91a091f4606710fba4e9327fd71e0e738
llama : add option to override model tensor buffers (#11397)

* llama : add option to override tensor buffers

* ggml : fix possible underflow in ggml_nbytes
12 files changed:
common/arg.cpp
common/common.cpp
common/common.h
ggml/src/ggml.c
include/llama.h
src/llama-context.cpp
src/llama-model-loader.cpp
src/llama-model-loader.h
src/llama-model.cpp
src/llama-model.h
src/llama-quant.cpp
src/llama.cpp