]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8cd1bcf)
gguf-py : Numpy dequantization for most types (#8939)
authorcompilade <redacted>
Sun, 11 Aug 2024 18:45:41 +0000 (14:45 -0400)
committerGitHub <redacted>
Sun, 11 Aug 2024 18:45:41 +0000 (14:45 -0400)
commit4134999e01f31256b15342b41c4de9e2477c4a6c
tree985fb7d21d59cf826031f73b02698b2e84c11978tree
parent8cd1bcfd3fc9f2b5cbafd7fb7581b3278acec25fcommit | diff
gguf-py : Numpy dequantization for most types (#8939)

* gguf-py : Numpy dequantization for most types

* gguf-py : Numpy dequantization for grid-based i-quants
gguf-py/gguf/quants.py diff | blob | history
gguf-py/tests/test_quants.py [new file with mode: 0755] blob
Packaging of ggml-org/llama.cpp