add back Makefile and quantize.cpp in correct locations
This commit is contained in:
Alex Rozanski
parent
e0d648c817
commit
713b65df3e
|
|
@ -16,9 +16,9 @@ let package = Package(
|
|||
name: "llamaObjCxx",
|
||||
dependencies: [],
|
||||
path: "Sources/llamaObjCxx",
|
||||
publicHeadersPath: "include/public",
|
||||
publicHeadersPath: "headers",
|
||||
cxxSettings: [
|
||||
.headerSearchPath("include/private")
|
||||
.headerSearchPath("cpp")
|
||||
])
|
||||
],
|
||||
cLanguageStandard: .gnu11,
|
||||
|
|
|
|||
|
|
@ -0,0 +1,338 @@
|
|||
#include "ggml.h"
|
||||
|
||||
#include "utils.h"
|
||||
|
||||
#include <cassert>
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstring>
|
||||
#include <fstream>
|
||||
#include <map>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
#include <regex>
|
||||
|
||||
// TODO: move somewhere else
|
||||
#define QK 32
|
||||
|
||||
// default hparams (LLaMA76B)
|
||||
struct llama_hparams {
|
||||
int32_t n_vocab = 32000;
|
||||
int32_t n_ctx = 512; // this is provided as user input?
|
||||
int32_t n_embd = 4096;
|
||||
int32_t n_mult = 256;
|
||||
int32_t n_head = 32;
|
||||
int32_t n_layer = 32;
|
||||
int32_t n_rot = 64;
|
||||
int32_t f16 = 1;
|
||||
};
|
||||
|
||||
|
||||
// quantize a model
|
||||
bool llama_model_quantize(const std::string & fname_inp, const std::string & fname_out, int itype) {
|
||||
ggml_type type = GGML_TYPE_Q4_1;
|
||||
|
||||
switch (itype) {
|
||||
case 2: type = GGML_TYPE_Q4_0; break;
|
||||
case 3: type = GGML_TYPE_Q4_1; break;
|
||||
default: fprintf(stderr, "%s: invalid quantization type %d\n", __func__, itype); return 1;
|
||||
};
|
||||
|
||||
if (type != GGML_TYPE_Q4_0 && type != GGML_TYPE_Q4_1) {
|
||||
fprintf(stderr, "%s: invalid quantization type %d\n", __func__, type);
|
||||
return false;
|
||||
}
|
||||
|
||||
gpt_vocab vocab;
|
||||
|
||||
printf("%s: loading model from '%s'\n", __func__, fname_inp.c_str());
|
||||
|
||||
auto finp = std::ifstream(fname_inp, std::ios::binary);
|
||||
if (!finp) {
|
||||
fprintf(stderr, "%s: failed to open '%s' for reading\n", __func__, fname_inp.c_str());
|
||||
return false;
|
||||
}
|
||||
|
||||
auto fout = std::ofstream(fname_out, std::ios::binary);
|
||||
if (!fout) {
|
||||
fprintf(stderr, "%s: failed to open '%s' for writing\n", __func__, fname_out.c_str());
|
||||
return false;
|
||||
}
|
||||
|
||||
// verify magic
|
||||
{
|
||||
uint32_t magic;
|
||||
finp.read((char *) &magic, sizeof(magic));
|
||||
if (magic != 0x67676d6c) {
|
||||
fprintf(stderr, "%s: invalid model file '%s' (bad magic)\n", __func__, fname_inp.c_str());
|
||||
return false;
|
||||
}
|
||||
|
||||
fout.write((char *) &magic, sizeof(magic));
|
||||
}
|
||||
|
||||
llama_hparams hparams;
|
||||
|
||||
// load hparams
|
||||
{
|
||||
finp.read((char *) &hparams.n_vocab, sizeof(hparams.n_vocab));
|
||||
//finp.read((char *) &hparams.n_ctx, sizeof(hparams.n_ctx));
|
||||
finp.read((char *) &hparams.n_embd, sizeof(hparams.n_embd));
|
||||
finp.read((char *) &hparams.n_mult, sizeof(hparams.n_mult));
|
||||
finp.read((char *) &hparams.n_head, sizeof(hparams.n_head));
|
||||
finp.read((char *) &hparams.n_layer, sizeof(hparams.n_layer));
|
||||
finp.read((char *) &hparams.n_rot, sizeof(hparams.n_rot));
|
||||
finp.read((char *) &hparams.f16, sizeof(hparams.f16));
|
||||
|
||||
printf("%s: n_vocab = %d\n", __func__, hparams.n_vocab);
|
||||
printf("%s: n_ctx = %d\n", __func__, hparams.n_ctx);
|
||||
printf("%s: n_embd = %d\n", __func__, hparams.n_embd);
|
||||
printf("%s: n_mult = %d\n", __func__, hparams.n_mult);
|
||||
printf("%s: n_head = %d\n", __func__, hparams.n_head);
|
||||
printf("%s: n_layer = %d\n", __func__, hparams.n_layer);
|
||||
printf("%s: f16 = %d\n", __func__, hparams.f16);
|
||||
|
||||
fout.write((char *) &hparams.n_vocab, sizeof(hparams.n_vocab));
|
||||
//fout.write((char *) &hparams.n_ctx, sizeof(hparams.n_ctx));
|
||||
fout.write((char *) &hparams.n_embd, sizeof(hparams.n_embd));
|
||||
fout.write((char *) &hparams.n_mult, sizeof(hparams.n_mult));
|
||||
fout.write((char *) &hparams.n_head, sizeof(hparams.n_head));
|
||||
fout.write((char *) &hparams.n_layer, sizeof(hparams.n_layer));
|
||||
fout.write((char *) &hparams.n_rot, sizeof(hparams.n_rot));
|
||||
fout.write((char *) &itype, sizeof(hparams.f16));
|
||||
}
|
||||
|
||||
// load vocab
|
||||
{
|
||||
const int32_t n_vocab = hparams.n_vocab;
|
||||
|
||||
if (n_vocab != hparams.n_vocab) {
|
||||
fprintf(stderr, "%s: invalid model file '%s' (bad vocab size %d != %d)\n",
|
||||
__func__, fname_inp.c_str(), n_vocab, hparams.n_vocab);
|
||||
return false;
|
||||
}
|
||||
|
||||
std::string word;
|
||||
for (int i = 0; i < n_vocab; i++) {
|
||||
uint32_t len;
|
||||
finp.read ((char *) &len, sizeof(len));
|
||||
fout.write((char *) &len, sizeof(len));
|
||||
|
||||
word.resize(len);
|
||||
finp.read ((char *) word.data(), len);
|
||||
fout.write((char *) word.data(), len);
|
||||
|
||||
vocab.token_to_id[word] = i;
|
||||
vocab.id_to_token[i] = word;
|
||||
}
|
||||
}
|
||||
|
||||
// load weights
|
||||
{
|
||||
size_t total_size_org = 0;
|
||||
size_t total_size_new = 0;
|
||||
|
||||
std::vector<float> work;
|
||||
|
||||
std::vector<uint8_t> data_u8;
|
||||
std::vector<ggml_fp16_t> data_f16;
|
||||
std::vector<float> data_f32;
|
||||
|
||||
std::vector<int64_t> hist_all(1 << 4, 0);
|
||||
|
||||
while (true) {
|
||||
int32_t n_dims;
|
||||
int32_t length;
|
||||
int32_t ftype;
|
||||
|
||||
finp.read(reinterpret_cast<char *>(&n_dims), sizeof(n_dims));
|
||||
finp.read(reinterpret_cast<char *>(&length), sizeof(length));
|
||||
finp.read(reinterpret_cast<char *>(&ftype), sizeof(ftype));
|
||||
|
||||
if (finp.eof()) {
|
||||
break;
|
||||
}
|
||||
|
||||
int32_t nelements = 1;
|
||||
int32_t ne[2] = { 1, 1 };
|
||||
for (int i = 0; i < n_dims; ++i) {
|
||||
finp.read (reinterpret_cast<char *>(&ne[i]), sizeof(ne[i]));
|
||||
nelements *= ne[i];
|
||||
}
|
||||
|
||||
std::string name(length, 0);
|
||||
finp.read (&name[0], length);
|
||||
|
||||
{
|
||||
static const char * ftype_str[] = { "f32", "f16", "q4_0", "q4_1", };
|
||||
printf("%48s - [%5d, %5d], type = %6s ", name.data(), ne[0], ne[1], ftype_str[ftype]);
|
||||
}
|
||||
|
||||
// regexes of tensor names to be quantized
|
||||
const std::vector<std::string> k_names = {
|
||||
".*weight",
|
||||
};
|
||||
|
||||
bool quantize = false;
|
||||
for (const auto & s : k_names) {
|
||||
if (std::regex_match(name, std::regex(s))) {
|
||||
quantize = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// quantize only 2D tensors
|
||||
quantize &= (n_dims == 2);
|
||||
|
||||
if (quantize) {
|
||||
if (ftype != 0 && ftype != 1) {
|
||||
fprintf(stderr, "%s: unsupported ftype %d for integer quantization\n", __func__, ftype);
|
||||
return false;
|
||||
}
|
||||
|
||||
if (ftype == 1) {
|
||||
data_f16.resize(nelements);
|
||||
finp.read(reinterpret_cast<char *>(data_f16.data()), nelements * sizeof(ggml_fp16_t));
|
||||
data_f32.resize(nelements);
|
||||
for (int i = 0; i < nelements; ++i) {
|
||||
data_f32[i] = ggml_fp16_to_fp32(data_f16[i]);
|
||||
}
|
||||
} else {
|
||||
data_f32.resize(nelements);
|
||||
finp.read(reinterpret_cast<char *>(data_f32.data()), nelements * sizeof(float));
|
||||
}
|
||||
|
||||
ftype = itype;
|
||||
} else {
|
||||
const int bpe = (ftype == 0) ? sizeof(float) : sizeof(uint16_t);
|
||||
|
||||
data_u8.resize(nelements*bpe);
|
||||
finp.read(reinterpret_cast<char *>(data_u8.data()), nelements * bpe);
|
||||
}
|
||||
|
||||
fout.write(reinterpret_cast<char *>(&n_dims), sizeof(n_dims));
|
||||
fout.write(reinterpret_cast<char *>(&length), sizeof(length));
|
||||
fout.write(reinterpret_cast<char *>(&ftype), sizeof(ftype));
|
||||
for (int i = 0; i < n_dims; ++i) {
|
||||
fout.write(reinterpret_cast<char *>(&ne[i]), sizeof(ne[i]));
|
||||
}
|
||||
fout.write(&name[0], length);
|
||||
|
||||
if (quantize) {
|
||||
printf("quantizing .. ");
|
||||
work.resize(nelements); // for quantization
|
||||
|
||||
size_t cur_size = 0;
|
||||
std::vector<int64_t> hist_cur(1 << 4, 0);
|
||||
|
||||
switch (type) {
|
||||
case GGML_TYPE_Q4_0:
|
||||
{
|
||||
cur_size = ggml_quantize_q4_0(data_f32.data(), work.data(), nelements, ne[0], QK, hist_cur.data());
|
||||
} break;
|
||||
case GGML_TYPE_Q4_1:
|
||||
{
|
||||
cur_size = ggml_quantize_q4_1(data_f32.data(), work.data(), nelements, ne[0], QK, hist_cur.data());
|
||||
} break;
|
||||
default:
|
||||
{
|
||||
fprintf(stderr, "%s: unsupported quantization type %d\n", __func__, type);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
fout.write(reinterpret_cast<char *>(work.data()), cur_size);
|
||||
total_size_new += cur_size;
|
||||
|
||||
printf("size = %8.2f MB -> %8.2f MB | hist: ", nelements * sizeof(float)/1024.0/1024.0, cur_size/1024.0/1024.0);
|
||||
for (int i = 0; i < hist_cur.size(); ++i) {
|
||||
hist_all[i] += hist_cur[i];
|
||||
}
|
||||
|
||||
for (int i = 0; i < hist_cur.size(); ++i) {
|
||||
printf("%5.3f ", hist_cur[i] / (float)nelements);
|
||||
}
|
||||
printf("\n");
|
||||
} else {
|
||||
printf("size = %8.3f MB\n", data_u8.size()/1024.0/1024.0);
|
||||
fout.write(reinterpret_cast<char *>(data_u8.data()), data_u8.size());
|
||||
total_size_new += data_u8.size();
|
||||
}
|
||||
|
||||
total_size_org += nelements * sizeof(float);
|
||||
}
|
||||
|
||||
printf("%s: model size = %8.2f MB\n", __func__, total_size_org/1024.0/1024.0);
|
||||
printf("%s: quant size = %8.2f MB\n", __func__, total_size_new/1024.0/1024.0);
|
||||
|
||||
{
|
||||
int64_t sum_all = 0;
|
||||
for (int i = 0; i < hist_all.size(); ++i) {
|
||||
sum_all += hist_all[i];
|
||||
}
|
||||
|
||||
printf("%s: hist: ", __func__);
|
||||
for (int i = 0; i < hist_all.size(); ++i) {
|
||||
printf("%5.3f ", hist_all[i] / (float)sum_all);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
}
|
||||
|
||||
finp.close();
|
||||
fout.close();
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
// usage:
|
||||
// ./llama-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\n", argv[0]);
|
||||
fprintf(stderr, " type = 2 - q4_0\n");
|
||||
fprintf(stderr, " type = 3 - q4_1\n");
|
||||
return 1;
|
||||
}
|
||||
|
||||
// needed to initialize f16 tables
|
||||
{
|
||||
struct ggml_init_params params = { 0, NULL };
|
||||
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 int itype = atoi(argv[3]);
|
||||
|
||||
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, fname_out, itype)) {
|
||||
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/1000.0f);
|
||||
printf("%s: total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us)/1000.0f);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -0,0 +1 @@
|
|||
../cpp
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
module llamaObjCxx {
|
||||
umbrella "include/public"
|
||||
umbrella "headers"
|
||||
export *
|
||||
}
|
||||
|
|
|
|||
|
|
@ -7,6 +7,12 @@
|
|||
objects = {
|
||||
|
||||
/* Begin PBXBuildFile section */
|
||||
8227D27229C2A844003E3197 /* LlamaEvent.h in Headers */ = {isa = PBXBuildFile; fileRef = 8227D26E29C2A844003E3197 /* LlamaEvent.h */; settings = {ATTRIBUTES = (Private, ); }; };
|
||||
8227D27329C2A844003E3197 /* LlamaRunnerBridge.h in Headers */ = {isa = PBXBuildFile; fileRef = 8227D26F29C2A844003E3197 /* LlamaRunnerBridge.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
8227D27429C2A844003E3197 /* LlamaError.h in Headers */ = {isa = PBXBuildFile; fileRef = 8227D27029C2A844003E3197 /* LlamaError.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
8227D27529C2A844003E3197 /* LlamaRunnerBridgeConfig.h in Headers */ = {isa = PBXBuildFile; fileRef = 8227D27129C2A844003E3197 /* LlamaRunnerBridgeConfig.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
8227D27729C2A87E003E3197 /* ggml.h in Headers */ = {isa = PBXBuildFile; fileRef = 8227D27629C2A87E003E3197 /* ggml.h */; settings = {ATTRIBUTES = (Private, ); }; };
|
||||
8227D27929C2A883003E3197 /* utils.h in Headers */ = {isa = PBXBuildFile; fileRef = 8227D27829C2A883003E3197 /* utils.h */; settings = {ATTRIBUTES = (Private, ); }; };
|
||||
82293E5B29BDC71700C67BD9 /* main.swift in Sources */ = {isa = PBXBuildFile; fileRef = 82293E5A29BDC71700C67BD9 /* main.swift */; };
|
||||
82293E6229BDC73100C67BD9 /* llama.framework in Frameworks */ = {isa = PBXBuildFile; fileRef = 82293E3929BDC4ED00C67BD9 /* llama.framework */; };
|
||||
82293E6529BDC7E200C67BD9 /* LlamaRunner.swift in Sources */ = {isa = PBXBuildFile; fileRef = 82293E6429BDC7E200C67BD9 /* LlamaRunner.swift */; };
|
||||
|
|
@ -18,12 +24,6 @@
|
|||
82819FB729C1DB5800399B7E /* LlamaPredictOperation.hh in Headers */ = {isa = PBXBuildFile; fileRef = 82819F8F29BF387400399B7E /* LlamaPredictOperation.hh */; settings = {ATTRIBUTES = (Private, ); }; };
|
||||
82819FB929C1DB5E00399B7E /* ggml.c in Sources */ = {isa = PBXBuildFile; fileRef = 82819F7D29BF2BFC00399B7E /* ggml.c */; };
|
||||
82819FBA29C1DB5E00399B7E /* utils.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 82819F8129BF2BFC00399B7E /* utils.cpp */; };
|
||||
82819FBB29C1DB6900399B7E /* LlamaError.h in Headers */ = {isa = PBXBuildFile; fileRef = 82819F9729C07BC900399B7E /* LlamaError.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
82819FBC29C1DB6E00399B7E /* LlamaEvent.h in Headers */ = {isa = PBXBuildFile; fileRef = 82819F9429C0526100399B7E /* LlamaEvent.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
82819FBD29C1DB7100399B7E /* LlamaRunnerBridge.h in Headers */ = {isa = PBXBuildFile; fileRef = 82293E5029BDC5DE00C67BD9 /* LlamaRunnerBridge.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
82819FBE29C1DB7500399B7E /* LlamaRunnerBridgeConfig.h in Headers */ = {isa = PBXBuildFile; fileRef = 82819F8B29BF2F5800399B7E /* LlamaRunnerBridgeConfig.h */; settings = {ATTRIBUTES = (Public, ); }; };
|
||||
82819FBF29C1DB7A00399B7E /* ggml.h in Headers */ = {isa = PBXBuildFile; fileRef = 82819FA029C1D72400399B7E /* ggml.h */; settings = {ATTRIBUTES = (Private, ); }; };
|
||||
82819FC029C1DB7D00399B7E /* utils.h in Headers */ = {isa = PBXBuildFile; fileRef = 82819FA129C1D72400399B7E /* utils.h */; settings = {ATTRIBUTES = (Private, ); }; };
|
||||
82819FC529C2585700399B7E /* libllamaObjCxx.a in Frameworks */ = {isa = PBXBuildFile; fileRef = 82819FA929C1DB2900399B7E /* libllamaObjCxx.a */; };
|
||||
/* End PBXBuildFile section */
|
||||
|
||||
|
|
@ -57,8 +57,13 @@
|
|||
/* End PBXCopyFilesBuildPhase section */
|
||||
|
||||
/* Begin PBXFileReference section */
|
||||
8227D26E29C2A844003E3197 /* LlamaEvent.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = LlamaEvent.h; sourceTree = "<group>"; };
|
||||
8227D26F29C2A844003E3197 /* LlamaRunnerBridge.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = LlamaRunnerBridge.h; sourceTree = "<group>"; };
|
||||
8227D27029C2A844003E3197 /* LlamaError.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = LlamaError.h; sourceTree = "<group>"; };
|
||||
8227D27129C2A844003E3197 /* LlamaRunnerBridgeConfig.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = LlamaRunnerBridgeConfig.h; sourceTree = "<group>"; };
|
||||
8227D27629C2A87E003E3197 /* ggml.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; name = ggml.h; path = Sources/cpp/ggml.h; sourceTree = SOURCE_ROOT; };
|
||||
8227D27829C2A883003E3197 /* utils.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; name = utils.h; path = Sources/cpp/utils.h; sourceTree = SOURCE_ROOT; };
|
||||
82293E3929BDC4ED00C67BD9 /* llama.framework */ = {isa = PBXFileReference; explicitFileType = wrapper.framework; includeInIndex = 0; path = llama.framework; sourceTree = BUILT_PRODUCTS_DIR; };
|
||||
82293E5029BDC5DE00C67BD9 /* LlamaRunnerBridge.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = LlamaRunnerBridge.h; sourceTree = "<group>"; };
|
||||
82293E5129BDC5DE00C67BD9 /* LlamaRunnerBridge.mm */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.objcpp; path = LlamaRunnerBridge.mm; sourceTree = "<group>"; };
|
||||
82293E5829BDC71700C67BD9 /* llamaTest */ = {isa = PBXFileReference; explicitFileType = "compiled.mach-o.executable"; includeInIndex = 0; path = llamaTest; sourceTree = BUILT_PRODUCTS_DIR; };
|
||||
82293E5A29BDC71700C67BD9 /* main.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = main.swift; sourceTree = "<group>"; };
|
||||
|
|
@ -67,19 +72,14 @@
|
|||
82819F7C29BDF7CB00399B7E /* LlamaTest.xcconfig */ = {isa = PBXFileReference; lastKnownFileType = text.xcconfig; path = LlamaTest.xcconfig; sourceTree = "<group>"; };
|
||||
82819F7D29BF2BFC00399B7E /* ggml.c */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.c; name = ggml.c; path = Sources/llamaObjCxx/cpp/ggml.c; sourceTree = SOURCE_ROOT; };
|
||||
82819F8129BF2BFC00399B7E /* utils.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = utils.cpp; path = Sources/llamaObjCxx/cpp/utils.cpp; sourceTree = SOURCE_ROOT; };
|
||||
82819F8B29BF2F5800399B7E /* LlamaRunnerBridgeConfig.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = LlamaRunnerBridgeConfig.h; sourceTree = "<group>"; };
|
||||
82819F8C29BF2F5800399B7E /* LlamaRunnerBridgeConfig.m */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.objc; path = LlamaRunnerBridgeConfig.m; sourceTree = "<group>"; };
|
||||
82819F8F29BF387400399B7E /* LlamaPredictOperation.hh */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.h; path = LlamaPredictOperation.hh; sourceTree = "<group>"; };
|
||||
82819F9029BF387400399B7E /* LlamaPredictOperation.mm */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.objcpp; path = LlamaPredictOperation.mm; sourceTree = "<group>"; };
|
||||
82819F9329C0526100399B7E /* LlamaEvent.mm */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.cpp.objcpp; path = LlamaEvent.mm; sourceTree = "<group>"; };
|
||||
82819F9429C0526100399B7E /* LlamaEvent.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = LlamaEvent.h; sourceTree = "<group>"; };
|
||||
82819F9729C07BC900399B7E /* LlamaError.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = LlamaError.h; sourceTree = "<group>"; };
|
||||
82819F9829C07BC900399B7E /* LlamaError.m */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.objc; path = LlamaError.m; sourceTree = "<group>"; };
|
||||
82819F9B29C0881800399B7E /* README.md */ = {isa = PBXFileReference; lastKnownFileType = net.daringfireball.markdown; path = README.md; sourceTree = "<group>"; };
|
||||
82819F9C29C0897900399B7E /* LICENSE */ = {isa = PBXFileReference; lastKnownFileType = text; path = LICENSE; sourceTree = "<group>"; };
|
||||
82819F9D29C1CCA300399B7E /* Package.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = Package.swift; sourceTree = "<group>"; };
|
||||
82819FA029C1D72400399B7E /* ggml.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = ggml.h; sourceTree = "<group>"; };
|
||||
82819FA129C1D72400399B7E /* utils.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = utils.h; sourceTree = "<group>"; };
|
||||
82819FA929C1DB2900399B7E /* libllamaObjCxx.a */ = {isa = PBXFileReference; explicitFileType = archive.ar; includeInIndex = 0; path = libllamaObjCxx.a; sourceTree = BUILT_PRODUCTS_DIR; };
|
||||
82819FC729C2939100399B7E /* module.modulemap */ = {isa = PBXFileReference; lastKnownFileType = "sourcecode.module-map"; path = module.modulemap; sourceTree = "<group>"; };
|
||||
/* End PBXFileReference section */
|
||||
|
|
@ -111,6 +111,17 @@
|
|||
/* End PBXFrameworksBuildPhase section */
|
||||
|
||||
/* Begin PBXGroup section */
|
||||
8227D26D29C2A825003E3197 /* headers */ = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
8227D27029C2A844003E3197 /* LlamaError.h */,
|
||||
8227D26E29C2A844003E3197 /* LlamaEvent.h */,
|
||||
8227D26F29C2A844003E3197 /* LlamaRunnerBridge.h */,
|
||||
8227D27129C2A844003E3197 /* LlamaRunnerBridgeConfig.h */,
|
||||
);
|
||||
path = headers;
|
||||
sourceTree = "<group>";
|
||||
};
|
||||
82293E2F29BDC4ED00C67BD9 = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
|
|
@ -146,7 +157,9 @@
|
|||
isa = PBXGroup;
|
||||
children = (
|
||||
82819F7D29BF2BFC00399B7E /* ggml.c */,
|
||||
8227D27629C2A87E003E3197 /* ggml.h */,
|
||||
82819F8129BF2BFC00399B7E /* utils.cpp */,
|
||||
8227D27829C2A883003E3197 /* utils.h */,
|
||||
);
|
||||
path = cpp;
|
||||
sourceTree = "<group>";
|
||||
|
|
@ -187,40 +200,11 @@
|
|||
82819F9829C07BC900399B7E /* LlamaError.m */,
|
||||
82293E6329BDC75F00C67BD9 /* bridge */,
|
||||
82293E4329BDC51A00C67BD9 /* cpp */,
|
||||
82819FA429C1DAD800399B7E /* include */,
|
||||
8227D26D29C2A825003E3197 /* headers */,
|
||||
);
|
||||
path = llamaObjCxx;
|
||||
sourceTree = "<group>";
|
||||
};
|
||||
82819F9F29C1CFAA00399B7E /* public */ = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
82819F9729C07BC900399B7E /* LlamaError.h */,
|
||||
82819F9429C0526100399B7E /* LlamaEvent.h */,
|
||||
82293E5029BDC5DE00C67BD9 /* LlamaRunnerBridge.h */,
|
||||
82819F8B29BF2F5800399B7E /* LlamaRunnerBridgeConfig.h */,
|
||||
);
|
||||
path = public;
|
||||
sourceTree = "<group>";
|
||||
};
|
||||
82819FA329C1D9BF00399B7E /* private */ = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
82819FA029C1D72400399B7E /* ggml.h */,
|
||||
82819FA129C1D72400399B7E /* utils.h */,
|
||||
);
|
||||
path = private;
|
||||
sourceTree = "<group>";
|
||||
};
|
||||
82819FA429C1DAD800399B7E /* include */ = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
82819FA329C1D9BF00399B7E /* private */,
|
||||
82819F9F29C1CFAA00399B7E /* public */,
|
||||
);
|
||||
path = include;
|
||||
sourceTree = "<group>";
|
||||
};
|
||||
82819FC629C289B400399B7E /* Sources */ = {
|
||||
isa = PBXGroup;
|
||||
children = (
|
||||
|
|
@ -244,13 +228,13 @@
|
|||
isa = PBXHeadersBuildPhase;
|
||||
buildActionMask = 2147483647;
|
||||
files = (
|
||||
82819FBC29C1DB6E00399B7E /* LlamaEvent.h in Headers */,
|
||||
82819FB729C1DB5800399B7E /* LlamaPredictOperation.hh in Headers */,
|
||||
82819FC029C1DB7D00399B7E /* utils.h in Headers */,
|
||||
82819FBB29C1DB6900399B7E /* LlamaError.h in Headers */,
|
||||
82819FBF29C1DB7A00399B7E /* ggml.h in Headers */,
|
||||
82819FBE29C1DB7500399B7E /* LlamaRunnerBridgeConfig.h in Headers */,
|
||||
82819FBD29C1DB7100399B7E /* LlamaRunnerBridge.h in Headers */,
|
||||
8227D27329C2A844003E3197 /* LlamaRunnerBridge.h in Headers */,
|
||||
8227D27929C2A883003E3197 /* utils.h in Headers */,
|
||||
8227D27229C2A844003E3197 /* LlamaEvent.h in Headers */,
|
||||
8227D27729C2A87E003E3197 /* ggml.h in Headers */,
|
||||
8227D27529C2A844003E3197 /* LlamaRunnerBridgeConfig.h in Headers */,
|
||||
8227D27429C2A844003E3197 /* LlamaError.h in Headers */,
|
||||
);
|
||||
runOnlyForDeploymentPostprocessing = 0;
|
||||
};
|
||||
|
|
|
|||
|
|
@ -0,0 +1,204 @@
|
|||
ifndef UNAME_S
|
||||
UNAME_S := $(shell uname -s)
|
||||
endif
|
||||
|
||||
ifndef UNAME_P
|
||||
UNAME_P := $(shell uname -p)
|
||||
endif
|
||||
|
||||
ifndef UNAME_M
|
||||
UNAME_M := $(shell uname -m)
|
||||
endif
|
||||
|
||||
CCV := $(shell $(CC) --version | head -n 1)
|
||||
CXXV := $(shell $(CXX) --version | head -n 1)
|
||||
|
||||
# Mac OS + Arm can report x86_64
|
||||
# ref: https://github.com/ggerganov/whisper.cpp/issues/66#issuecomment-1282546789
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
ifneq ($(UNAME_P),arm)
|
||||
SYSCTL_M := $(shell sysctl -n hw.optional.arm64)
|
||||
ifeq ($(SYSCTL_M),1)
|
||||
# UNAME_P := arm
|
||||
# UNAME_M := arm64
|
||||
warn := $(warning Your arch is announced as x86_64, but it seems to actually be ARM64. Not fixing that can lead to bad performance. For more info see: https://github.com/ggerganov/whisper.cpp/issues/66\#issuecomment-1282546789)
|
||||
endif
|
||||
endif
|
||||
endif
|
||||
|
||||
#
|
||||
# Compile flags
|
||||
#
|
||||
|
||||
CPP_PATH = ../Sources/cpp
|
||||
CFLAGS = -I. -I../Sources/llamaObjCxx/include/private/ -O3 -DNDEBUG -std=c11 -fPIC
|
||||
CXXFLAGS = -I. -I../Sources/llamaObjCxx/include/private/ -O3 -DNDEBUG -std=c++11 -fPIC
|
||||
LDFLAGS =
|
||||
|
||||
# OS specific
|
||||
# TODO: support Windows
|
||||
ifeq ($(UNAME_S),Linux)
|
||||
CFLAGS += -pthread
|
||||
CXXFLAGS += -pthread
|
||||
endif
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
CFLAGS += -pthread
|
||||
CXXFLAGS += -pthread
|
||||
endif
|
||||
ifeq ($(UNAME_S),FreeBSD)
|
||||
CFLAGS += -pthread
|
||||
CXXFLAGS += -pthread
|
||||
endif
|
||||
ifeq ($(UNAME_S),NetBSD)
|
||||
CFLAGS += -pthread
|
||||
CXXFLAGS += -pthread
|
||||
endif
|
||||
ifeq ($(UNAME_S),Haiku)
|
||||
CFLAGS += -pthread
|
||||
CXXFLAGS += -pthread
|
||||
endif
|
||||
|
||||
# Architecture specific
|
||||
# TODO: probably these flags need to be tweaked on some architectures
|
||||
# feel free to update the Makefile for your architecture and send a pull request or issue
|
||||
ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686))
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
CFLAGS += -mf16c
|
||||
AVX1_M := $(shell sysctl machdep.cpu.features)
|
||||
ifneq (,$(findstring FMA,$(AVX1_M)))
|
||||
CFLAGS += -mfma
|
||||
endif
|
||||
ifneq (,$(findstring AVX1.0,$(AVX1_M)))
|
||||
CFLAGS += -mavx
|
||||
endif
|
||||
AVX2_M := $(shell sysctl machdep.cpu.leaf7_features)
|
||||
ifneq (,$(findstring AVX2,$(AVX2_M)))
|
||||
CFLAGS += -mavx2
|
||||
endif
|
||||
else ifeq ($(UNAME_S),Linux)
|
||||
AVX1_M := $(shell grep "avx " /proc/cpuinfo)
|
||||
ifneq (,$(findstring avx,$(AVX1_M)))
|
||||
CFLAGS += -mavx
|
||||
endif
|
||||
AVX2_M := $(shell grep "avx2 " /proc/cpuinfo)
|
||||
ifneq (,$(findstring avx2,$(AVX2_M)))
|
||||
CFLAGS += -mavx2
|
||||
endif
|
||||
FMA_M := $(shell grep "fma " /proc/cpuinfo)
|
||||
ifneq (,$(findstring fma,$(FMA_M)))
|
||||
CFLAGS += -mfma
|
||||
endif
|
||||
F16C_M := $(shell grep "f16c " /proc/cpuinfo)
|
||||
ifneq (,$(findstring f16c,$(F16C_M)))
|
||||
CFLAGS += -mf16c
|
||||
endif
|
||||
SSE3_M := $(shell grep "sse3 " /proc/cpuinfo)
|
||||
ifneq (,$(findstring sse3,$(SSE3_M)))
|
||||
CFLAGS += -msse3
|
||||
endif
|
||||
else ifeq ($(UNAME_S),Haiku)
|
||||
AVX1_M := $(shell sysinfo -cpu | grep "AVX ")
|
||||
ifneq (,$(findstring avx,$(AVX1_M)))
|
||||
CFLAGS += -mavx
|
||||
endif
|
||||
AVX2_M := $(shell sysinfo -cpu | grep "AVX2 ")
|
||||
ifneq (,$(findstring avx2,$(AVX2_M)))
|
||||
CFLAGS += -mavx2
|
||||
endif
|
||||
FMA_M := $(shell sysinfo -cpu | grep "FMA ")
|
||||
ifneq (,$(findstring fma,$(FMA_M)))
|
||||
CFLAGS += -mfma
|
||||
endif
|
||||
F16C_M := $(shell sysinfo -cpu | grep "F16C ")
|
||||
ifneq (,$(findstring f16c,$(F16C_M)))
|
||||
CFLAGS += -mf16c
|
||||
endif
|
||||
else
|
||||
CFLAGS += -mfma -mf16c -mavx -mavx2
|
||||
endif
|
||||
endif
|
||||
ifeq ($(UNAME_M),amd64)
|
||||
CFLAGS += -mavx -mavx2 -mfma -mf16c
|
||||
endif
|
||||
ifneq ($(filter ppc64%,$(UNAME_M)),)
|
||||
POWER9_M := $(shell grep "POWER9" /proc/cpuinfo)
|
||||
ifneq (,$(findstring POWER9,$(POWER9_M)))
|
||||
CFLAGS += -mpower9-vector
|
||||
endif
|
||||
# Require c++23's std::byteswap for big-endian support.
|
||||
ifeq ($(UNAME_M),ppc64)
|
||||
CXXFLAGS += -std=c++23 -DGGML_BIG_ENDIAN
|
||||
endif
|
||||
endif
|
||||
ifndef LLAMA_NO_ACCELERATE
|
||||
# Mac M1 - include Accelerate framework
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
CFLAGS += -DGGML_USE_ACCELERATE
|
||||
LDFLAGS += -framework Accelerate
|
||||
endif
|
||||
endif
|
||||
ifdef LLAMA_OPENBLAS
|
||||
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas
|
||||
LDFLAGS += -lopenblas
|
||||
endif
|
||||
ifdef LLAMA_GPROF
|
||||
CFLAGS += -pg
|
||||
CXXFLAGS += -pg
|
||||
endif
|
||||
ifneq ($(filter aarch64%,$(UNAME_M)),)
|
||||
CFLAGS += -mcpu=native
|
||||
CXXFLAGS += -mcpu=native
|
||||
endif
|
||||
ifneq ($(filter armv6%,$(UNAME_M)),)
|
||||
# Raspberry Pi 1, 2, 3
|
||||
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access
|
||||
endif
|
||||
ifneq ($(filter armv7%,$(UNAME_M)),)
|
||||
# Raspberry Pi 4
|
||||
CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
|
||||
endif
|
||||
ifneq ($(filter armv8%,$(UNAME_M)),)
|
||||
# Raspberry Pi 4
|
||||
CFLAGS += -mfp16-format=ieee -mno-unaligned-access
|
||||
endif
|
||||
|
||||
#
|
||||
# Print build information
|
||||
#
|
||||
|
||||
$(info I llama.cpp build info: )
|
||||
$(info I UNAME_S: $(UNAME_S))
|
||||
$(info I UNAME_P: $(UNAME_P))
|
||||
$(info I UNAME_M: $(UNAME_M))
|
||||
$(info I CFLAGS: $(CFLAGS))
|
||||
$(info I CXXFLAGS: $(CXXFLAGS))
|
||||
$(info I LDFLAGS: $(LDFLAGS))
|
||||
$(info I CC: $(CCV))
|
||||
$(info I CXX: $(CXXV))
|
||||
$(info )
|
||||
|
||||
default: quantize
|
||||
|
||||
#
|
||||
# Build library
|
||||
#
|
||||
|
||||
ggml.o: $(CPP_PATH)/ggml.c $(CPP_PATH)/ggml.h
|
||||
$(CC) $(CFLAGS) -c $(CPP_PATH)/ggml.c -o ggml.o
|
||||
|
||||
utils.o: $(CPP_PATH)/utils.cpp $(CPP_PATH)/utils.h
|
||||
$(CXX) $(CXXFLAGS) -c $(CPP_PATH)/utils.cpp -o utils.o
|
||||
|
||||
clean:
|
||||
rm -f *.o quantize
|
||||
|
||||
quantize: $(CPP_PATH)/utils.cpp ggml.o utils.o
|
||||
$(CXX) $(CXXFLAGS) $(CPP_PATH)/quantize.cpp ggml.o utils.o -o quantize $(LDFLAGS)
|
||||
|
||||
#
|
||||
# Tests
|
||||
#
|
||||
|
||||
.PHONY: tests
|
||||
tests:
|
||||
bash ./tests/run-tests.sh
|
||||
Binary file not shown.
Loading…
Reference in New Issue