]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3fe8d7a)
gguf-py : add support for I8, I16 and I32 (#6045)
authorOndřej Čertík <redacted>
Thu, 14 Mar 2024 10:40:14 +0000 (04:40 -0600)
committerGitHub <redacted>
Thu, 14 Mar 2024 10:40:14 +0000 (12:40 +0200)
commit3ca23481dd309bd51cc31c73a4cc34f922cc372f
treeeab44b8528241eab625347f2a5791a3f64d682d0tree
parent3fe8d7a17f84bd721cd4d8db35365da44b69f68bcommit | diff
gguf-py : add support for I8, I16 and I32 (#6045)

* Refactor dtype handling to be extensible

This code is equivalent as before, but now it is prepared to easily add
more NumPy dtypes.

* Add support for I8, I16 and I32

These types are allowed in the GGUF specification.

* Add support for I8, I16 and I32 to gguf_writer

* Add support for I8, I16, I32 to gguf_reader
gguf-py/gguf/constants.py diff | blob | history
gguf-py/gguf/gguf_reader.py diff | blob | history
gguf-py/gguf/gguf_writer.py diff | blob | history
Packaging of ggml-org/llama.cpp