]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 0bf47a1)
convert : handle pre-quantized models (#14810)
authorcompilade <redacted>
Thu, 23 Oct 2025 20:31:41 +0000 (16:31 -0400)
committerGitHub <redacted>
Thu, 23 Oct 2025 20:31:41 +0000 (16:31 -0400)
commitf8f071faddf32ea09f4234edb6e809b380a9ee26
tree8121c1bc59ef1c884445f6663b228e594ec99ce3tree
parent0bf47a1dbba4d36f2aff4e8c34b06210ba34e688commit | diff
convert : handle pre-quantized models (#14810)

* convert : begin handling pre-quantized models

* convert : fix conversion from FP8 for Deepseek-V3.1-Base
convert_hf_to_gguf.py diff | blob | history
Packaging of ggml-org/llama.cpp