]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 238005c)
quantize : handle user-defined pruning of whole layers (blocks) (#13037)
authorEd Addario <redacted>
Sun, 22 Jun 2025 21:16:26 +0000 (22:16 +0100)
committerGitHub <redacted>
Sun, 22 Jun 2025 21:16:26 +0000 (23:16 +0200)
commitfa4a9f2a1ccda2573189a9d4995bdf0bceb41156
tree9670bb7b6d14cd141284cfa81926608a6f46c413tree
parent238005c2dc67426cf678baa2d54c881701693288commit | diff
quantize : handle user-defined pruning of whole layers (blocks) (#13037)
include/llama.h diff | blob | history
src/llama-quant.cpp diff | blob | history
tools/quantize/quantize.cpp diff | blob | history
Packaging of ggml-org/llama.cpp