tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 12:19:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* gguf-py : add MXFP4 de/quantization support

* ggml-quants : handle zero amax for MXFP4
This commit is contained in:
compilade
2025-08-08 17:48:26 -04:00
committed by GitHub
parent 4850b52aed
commit e54d41befc
3 changed files with 67 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-quants.c
View File

@@ -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);