]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : fix non-quantization of expert gating tensors (#5754)
authorcompilade <redacted>
Wed, 28 Feb 2024 08:52:56 +0000 (03:52 -0500)
committerGitHub <redacted>
Wed, 28 Feb 2024 08:52:56 +0000 (10:52 +0200)
commitadcb12a9bad87bc96f2f158c95892b3d04aa7ffb
tree5b32e4c68a55d074658f4658da25fb5583f7889b
parent177628bfd85565070916ad66a5ac4071ee0527d8
llama : fix non-quantization of expert gating tensors (#5754)

This reverts a single line from #5475
llama.cpp