mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 02:44:36 +00:00
38de86a711
* Multi-threading quantization. Not much gain for simple quantizations, bit it will be important for quantizations that require more CPU cycles. * Multi-threading for quantize-stats It now does the job in ~14 seconds on my Mac for Q4_0, Q4_1 and Q4_2. Single-threaded it was taking more than 2 minutes after adding the more elaborate version of Q4_2. * Reviewer comments * Avoiding compiler confusion After changing chunk_size to const int as suggested by @ggerganov, clang and GCC starting to warn me that I don't need to capture it in the lambda. So, I removed it from the capture list. But that makes the MSVC build fail. So, making it a constexpr to make every compiler happy. * Still fighting with lambda captures in MSVC --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
62 lines
1.8 KiB
C++
62 lines
1.8 KiB
C++
#include "ggml.h"
|
|
#include "llama.h"
|
|
|
|
#include <cstdio>
|
|
#include <string>
|
|
|
|
// usage:
|
|
// ./quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
|
|
//
|
|
int main(int argc, char ** argv) {
|
|
ggml_time_init();
|
|
|
|
if (argc < 4) {
|
|
fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type [nthread]\n", argv[0]);
|
|
fprintf(stderr, " type = %d - q4_0\n", LLAMA_FTYPE_MOSTLY_Q4_0);
|
|
fprintf(stderr, " type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1);
|
|
fprintf(stderr, " type = %d - q4_2\n", LLAMA_FTYPE_MOSTLY_Q4_2);
|
|
fprintf(stderr, " type = %d - q4_3\n", LLAMA_FTYPE_MOSTLY_Q4_3);
|
|
return 1;
|
|
}
|
|
|
|
// needed to initialize f16 tables
|
|
{
|
|
struct ggml_init_params params = { 0, NULL, false };
|
|
struct ggml_context * ctx = ggml_init(params);
|
|
ggml_free(ctx);
|
|
}
|
|
|
|
const std::string fname_inp = argv[1];
|
|
const std::string fname_out = argv[2];
|
|
|
|
const enum llama_ftype ftype = (enum llama_ftype)atoi(argv[3]);
|
|
int nthread = argc > 4 ? atoi(argv[4]) : 0;
|
|
|
|
const int64_t t_main_start_us = ggml_time_us();
|
|
|
|
int64_t t_quantize_us = 0;
|
|
|
|
// load the model
|
|
{
|
|
const int64_t t_start_us = ggml_time_us();
|
|
|
|
if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), ftype, nthread)) {
|
|
fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());
|
|
return 1;
|
|
}
|
|
|
|
t_quantize_us = ggml_time_us() - t_start_us;
|
|
}
|
|
|
|
// report timing
|
|
{
|
|
const int64_t t_main_end_us = ggml_time_us();
|
|
|
|
printf("\n");
|
|
printf("%s: quantize time = %8.2f ms\n", __func__, t_quantize_us/1000.0);
|
|
printf("%s: total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us)/1000.0);
|
|
}
|
|
|
|
return 0;
|
|
}
|