|
ember.cpp 0.1.0
C++ inference engine for Llama-family and paperkiln models (CPU, CUDA, WebAssembly)
|
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 137 of file quantization.h.
| uint16_t block_q8_0::d |
Block scale
Definition at line 138 of file quantization.h.
| int8_t block_q8_0::qs[GGML_QK8_0] |
Quantized values
Definition at line 139 of file quantization.h.