mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-11-07 08:34:37 +01:00
794b162a46
* whisper : add integer quantization support * examples : add common-ggml + prepare to add "quantize" tool * whisper : quantization tool ready * whisper : fix F32 support * whisper : try to fix shared lib linkage * wasm : update quantized models to Q5 * bench.wasm : remove "medium" button * bench.wasm : fix custom model button * ggml : add Q5_0 and Q5_1 WASM SIMD * wasm : add quantized models to all WASM examples * wasm : bump DB version number to 2 * talk-llama : update example to latest llama.cpp * node : increase test timeout to 10s * readme : add information for model quantization * wasm : add links to other examples
19 lines
410 B
C++
19 lines
410 B
C++
#pragma once
|
|
|
|
#include "ggml.h"
|
|
|
|
#include <fstream>
|
|
#include <vector>
|
|
#include <string>
|
|
|
|
enum ggml_ftype ggml_parse_ftype(const char * str);
|
|
|
|
void ggml_print_ftypes(FILE * fp = stderr);
|
|
|
|
bool ggml_common_quantize_0(
|
|
std::ifstream & finp,
|
|
std::ofstream & fout,
|
|
const ggml_ftype ftype,
|
|
const std::vector<std::string> & to_quant,
|
|
const std::vector<std::string> & to_skip);
|