|
TinyLlama.cpp 1.0
A lightweight C++ implementation of the TinyLlama language model
|
Simple 8-bit quantized block structure. More...
#include <quantization.h>

Public Attributes | |
| uint16_t | d |
| int8_t | qs [GGML_QK8_0] |
Simple 8-bit quantized block structure.
Definition at line 120 of file quantization.h.
| uint16_t block_q8_0::d |
| int8_t block_q8_0::qs[GGML_QK8_0] |
Quantized values
Definition at line 122 of file quantization.h.
Referenced by dequantize_q8_0_block().