]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 55b7d6c)
Keep Minimax's indexer tensors at F32 for speed and accuracy (#26144)
authorBartowski <redacted>
Sun, 26 Jul 2026 22:02:56 +0000 (18:02 -0400)
committerGitHub <redacted>
Sun, 26 Jul 2026 22:02:56 +0000 (18:02 -0400)
commit7657a6c26a7c74480db23893c3b5cc68172dacd3
tree3a413a472d946ae9d158adf3b68db64eb30c3dcctree
parent55b7d6c4c7e518005bc320cf0139264411deac7fcommit | diff
Keep Minimax's indexer tensors at F32 for speed and accuracy (#26144)

* Keep Minimax's indexer tensors at F32 for speed and accuracy

* name -> new_name
conversion/minimax.py diff | blob | history
src/llama-quant.cpp diff | blob | history
Packaging of ggml-org/llama.cpp