]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
gguf-py : add Numpy MXFP4 de/quantization support (#15111)
authorcompilade <redacted>
Fri, 8 Aug 2025 21:48:26 +0000 (17:48 -0400)
committerGitHub <redacted>
Fri, 8 Aug 2025 21:48:26 +0000 (17:48 -0400)
commite54d41befcc1575f4c898c5ff4ef43970cead75f
tree92af305fd5e6be67f891bbdb6a57e6869f8141b3
parent4850b52aedceeb70bb4fe49f2d7cd1df6ee98682
gguf-py : add Numpy MXFP4 de/quantization support (#15111)

* gguf-py : add MXFP4 de/quantization support

* ggml-quants : handle zero amax for MXFP4
ggml/src/ggml-quants.c
gguf-py/gguf/quants.py
gguf-py/tests/test_quants.py