]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: dba1af6)
quantize: options for output and token embedding tensors qtype (#6239)
authorKawrakow <redacted>
Fri, 22 Mar 2024 18:47:14 +0000 (19:47 +0100)
committerGitHub <redacted>
Fri, 22 Mar 2024 18:47:14 +0000 (20:47 +0200)
commit1d0331c12a2f2a6296b471232bd4e66fbf06e6a1
tree4417697e55b3a70c97c6655b37491a485a3b9797tree
parentdba1af612926cbd4ebe2d876277af1e3305177e0commit | diff
quantize: options for output and token embedding tensors qtype (#6239)

* quantize: be able to specify the output tensor type

* quantize: be able to specify the token embedding tensor type

---------

Co-authored-by: Iwan Kawrakow <redacted>
examples/quantize/quantize.cpp diff | blob | history
llama.cpp diff | blob | history
llama.h diff | blob | history
Packaging of ggml-org/llama.cpp