gguf-py : add Numpy MXFP4 de/quantization support (llama/15111)

* gguf-py : add MXFP4 de/quantization support

* ggml-quants : handle zero amax for MXFP4

diff --git a/src/ggml-quants.c b/src/ggml-quants.c
index a57d2a16d6c540e8baca40138525d4813246a57b..94f6405ca1e059fb92f70e2a4d675e8083dc15e6 100644 (file)
--- a/src/ggml-quants.c
+++ b/src/ggml-quants.c
@@ -288,7 +288,7 @@ void quantize_row_mxfp4_ref(const float * GGML_RESTRICT x, block_mxfp4 * GGML_RE
             }
         }
 
-        const uint8_t e = (uint8_t) (floorf(log2f(amax)) - 2 + 127);
+        const uint8_t e = amax > 0.0f ? (uint8_t) (floorf(log2f(amax)) - 2 + 127) : 0;
 
         const float d = GGML_E8M0_TO_FP32_HALF(e);