LLM inference in C/C++
C++ ggml
gguf-py: fix Q8_1 block size in GGML_QUANT_SIZES (2+2+32) (#29036)
yanghongbb11ebb6820a
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.pyindex 36b4c3190e..27c126b365 100644--- a/gguf-py/gguf/constants.py+++ b/gguf-py/gguf/constants.py@@ -5876,7 +5876,7 @@ GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = {GGMLQuantizationType.Q5_0: (32, 2 + 4 + 16),GGMLQuantizationType.Q5_1: (32, 2 + 2 + 4 + 16),GGMLQuantizationType.Q8_0: (32, 2 + 32),- GGMLQuantizationType.Q8_1: (32, 4 + 4 + 32),+ GGMLQuantizationType.Q8_1: (32, 2 + 2 + 32),GGMLQuantizationType.Q2_K: (256, 2 + 2 + QK_K // 16 + QK_K // 4),GGMLQuantizationType.Q3_K: (256, 2 + QK_K // 4 + QK_K // 8 + 12),GGMLQuantizationType.Q4_K: (256, 2 + 2 + QK_K // 2 + 12),