From 62566a54365795cd509d8075cd2ea706d491d72f Mon Sep 17 00:00:00 2001 From: compilade Date: Fri, 8 Aug 2025 17:48:26 -0400 Subject: [PATCH] gguf-py : add Numpy MXFP4 de/quantization support (llama/15111) * gguf-py : add MXFP4 de/quantization support * ggml-quants : handle zero amax for MXFP4 --- ggml/src/ggml-quants.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml/src/ggml-quants.c b/ggml/src/ggml-quants.c index a57d2a16..94f6405c 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/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);