llama.cpp/tools/quantize/quantize.cpp at master · allozaur/llama.cpp · GitHub

History

655 lines (594 loc) · 26.6 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

#include "llama.h"

#include "build-info.h"

#include "common.h"

#include "imatrix-loader.h"

#include "gguf.h"

#include <algorithm>

#include <cctype>

#include <clocale>

#include <cmath>

#include <cstdio>

#include <cstring>

#include <vector>

#include <string>

#include <unordered_map>

#include <fstream>

#include <filesystem>

// result of parsing --tensor-type option

// changes to this struct must also be reflected in src/llama-quant.cpp

struct tensor_type_option {

std::string name;

ggml_type type = GGML_TYPE_COUNT;

};

struct quant_option {

std::string name;

llama_ftype ftype;

std::string desc;

};

static const std::vector<quant_option> QUANT_OPTIONS = {

{ "Q1_0", LLAMA_FTYPE_MOSTLY_Q1_0, " 1.125 bpw quantization", },

{ "Q2_0", LLAMA_FTYPE_MOSTLY_Q2_0, " 2.25 bpw quantization (group 64)", },

{ "Q4_0", LLAMA_FTYPE_MOSTLY_Q4_0, " 4.34G, +0.4685 ppl @ Llama-3-8B", },

{ "Q4_1", LLAMA_FTYPE_MOSTLY_Q4_1, " 4.78G, +0.4511 ppl @ Llama-3-8B", },

{ "MXFP4_MOE",LLAMA_FTYPE_MOSTLY_MXFP4_MOE," MXFP4 MoE", },

{ "Q5_0", LLAMA_FTYPE_MOSTLY_Q5_0, " 5.21G, +0.1316 ppl @ Llama-3-8B", },

{ "Q5_1", LLAMA_FTYPE_MOSTLY_Q5_1, " 5.65G, +0.1062 ppl @ Llama-3-8B", },

{ "IQ2_XXS", LLAMA_FTYPE_MOSTLY_IQ2_XXS, " 2.06 bpw quantization", },

{ "IQ2_XS", LLAMA_FTYPE_MOSTLY_IQ2_XS, " 2.31 bpw quantization", },

{ "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", },

{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", },

{ "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", },

{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },

{ "TQ1_0", LLAMA_FTYPE_MOSTLY_TQ1_0, " 1.69 bpw ternarization", },

{ "TQ2_0", LLAMA_FTYPE_MOSTLY_TQ2_0, " 2.06 bpw ternarization", },

{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.96G, +3.5199 ppl @ Llama-3-8B", },

{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.96G, +3.1836 ppl @ Llama-3-8B", },

{ "IQ3_XXS", LLAMA_FTYPE_MOSTLY_IQ3_XXS, " 3.06 bpw quantization", },

{ "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", },

{ "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", },

{ "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" },

{ "IQ3_XS", LLAMA_FTYPE_MOSTLY_IQ3_XS, " 3.3 bpw quantization", },

{ "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 3.41G, +1.6321 ppl @ Llama-3-8B", },

{ "Q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M, " 3.74G, +0.6569 ppl @ Llama-3-8B", },

{ "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 4.03G, +0.5562 ppl @ Llama-3-8B", },

{ "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", },

{ "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", },

{ "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", },

{ "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 4.37G, +0.2689 ppl @ Llama-3-8B", },

{ "Q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M, " 4.58G, +0.1754 ppl @ Llama-3-8B", },

{ "Q5_K", LLAMA_FTYPE_MOSTLY_Q5_K_M, "alias for Q5_K_M", },

{ "Q5_K_S", LLAMA_FTYPE_MOSTLY_Q5_K_S, " 5.21G, +0.1049 ppl @ Llama-3-8B", },

{ "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 5.33G, +0.0569 ppl @ Llama-3-8B", },

{ "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 6.14G, +0.0217 ppl @ Llama-3-8B", },

{ "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 7.96G, +0.0026 ppl @ Llama-3-8B", },

{ "F16", LLAMA_FTYPE_MOSTLY_F16, "14.00G, +0.0020 ppl @ Mistral-7B", },

{ "BF16", LLAMA_FTYPE_MOSTLY_BF16, "14.00G, -0.0050 ppl @ Mistral-7B", },

{ "F32", LLAMA_FTYPE_ALL_F32, "26.00G @ 7B", },

// Note: Ensure COPY comes after F32 to avoid ftype 0 from matching.

{ "COPY", LLAMA_FTYPE_ALL_F32, "only copy tensors, no quantizing", },

};

static const char * const LLM_KV_QUANTIZE_IMATRIX_FILE = "quantize.imatrix.file";

static const char * const LLM_KV_QUANTIZE_IMATRIX_DATASET = "quantize.imatrix.dataset";

static const char * const LLM_KV_QUANTIZE_IMATRIX_N_ENTRIES = "quantize.imatrix.entries_count";

static const char * const LLM_KV_QUANTIZE_IMATRIX_N_CHUNKS = "quantize.imatrix.chunks_count";

static bool striequals(const char * a, const char * b) {

while (*a && *b) {

if (std::tolower(*a) != std::tolower(*b)) {

return false;

}

a++; b++;

}

return *a == *b;

}

static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftype, std::string & ftype_str_out) {

std::string ftype_str;

for (auto ch : ftype_str_in) {

ftype_str.push_back(std::toupper(ch));

}

for (const auto & it : QUANT_OPTIONS) {

if (striequals(it.name.c_str(), ftype_str.c_str())) {

ftype = it.ftype;

ftype_str_out = it.name;

return true;

}

try {

int ftype_int = std::stoi(ftype_str);

for (const auto & it : QUANT_OPTIONS) {

if (it.ftype == ftype_int) {

ftype = it.ftype;

ftype_str_out = it.name;

return true;

}

catch (...) {

// stoi failed

}

return false;

}

[[noreturn]]

static void usage(const char * executable) {

printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] [--pure] [--imatrix] [--include-weights]\n", executable);

printf(" [--exclude-weights] [--output-tensor-type] [--token-embedding-type] [--tensor-type] [--tensor-type-file]\n");

printf(" [--prune-layers] [--keep-split] [--override-kv] [--dry-run]\n");

printf(" model-f32.gguf [model-quant.gguf] type [nthreads]\n\n");

printf(" --allow-requantize\n");

printf(" allow requantizing tensors that have already been quantized\n");

printf(" WARNING: this can severely reduce quality compared to quantizing\n");

printf(" from 16bit or 32bit!\n");

printf(" --leave-output-tensor\n");

printf(" leave output.weight un(re)quantized\n");

printf(" increases model size but may also increase quality, especially when requantizing\n");

printf(" --pure\n");

printf(" disable k-quant mixtures and quantize all tensors to the same type\n");

printf(" --imatrix file_name\n");

printf(" use data in file_name as importance matrix for quant optimizations\n");

printf(" --include-weights tensor_name\n");

printf(" use importance matrix for this/these tensor(s)\n");

printf(" --exclude-weights tensor_name\n");

printf(" do not use importance matrix for this/these tensor(s)\n");

printf(" --output-tensor-type ggml_type\n");

printf(" use this ggml_type for the output.weight tensor\n");

printf(" --token-embedding-type ggml_type\n");

printf(" use this ggml_type for the token embeddings tensor\n");

printf(" --tensor-type tensor_name=ggml_type\n");

printf(" quantize this tensor to this ggml_type\n");

printf(" this is an advanced option to selectively quantize tensors. may be specified multiple times.\n");

printf(" example: --tensor-type attn_q=q8_0\n");

printf(" --tensor-type-file tensor_types.txt\n");

printf(" list of tensors to quantize to a specific ggml_type\n");

printf(" this is an advanced option to selectively quantize a long list of tensors.\n");

printf(" the file should use the same format as above, separated by spaces or newlines.\n");

printf(" --prune-layers L0,L1,L2...\n");

printf(" comma-separated list of layer numbers to prune from the model\n");

printf(" WARNING: this is an advanced option, use with care.\n");

printf(" --keep-split\n");

printf(" generate quantized model in the same shards as input\n");

printf(" --override-kv KEY=TYPE:VALUE\n");

printf(" override model metadata by key in the quantized model. may be specified multiple times.\n");

printf(" WARNING: this is an advanced option, use with care.\n");

printf(" --dry-run\n");

printf(" calculate and show the final quantization size without performing quantization\n");

printf(" example: llama-quantize --dry-run model-f32.gguf Q4_K\n\n");

printf("note: --include-weights and --exclude-weights cannot be used together\n\n");

printf("-----------------------------------------------------------------------------\n");

printf(" allowed quantization types\n");

printf("-----------------------------------------------------------------------------\n\n");

for (const auto & it : QUANT_OPTIONS) {

if (it.name != "COPY") {

printf(" %2d or ", it.ftype);

} else {

printf(" ");

}

printf("%-7s : %s\n", it.name.c_str(), it.desc.c_str());

}

exit(1);

}

static int load_imatrix(const std::string & imatrix_file, std::vector<std::string> & imatrix_datasets, std::unordered_map<std::string, std::vector<float>> & imatrix_data) {

common_imatrix loaded;

if (!common_imatrix_load(imatrix_file, loaded)) {

fprintf(stderr, "%s: failed to load imatrix from '%s'\n", __func__, imatrix_file.c_str());

exit(1);

}

if (!loaded.is_legacy && !loaded.has_metadata) {

fprintf(stderr, "%s: missing imatrix metadata in file %s\n", __func__, imatrix_file.c_str());

exit(1);

}

for (const auto & [name, entry] : loaded.entries) {

auto & e = imatrix_data[name];

e.resize(entry.sums.size());

if (!loaded.is_legacy) {

// GGUF format: normalize by per-expert counts

const int64_t ncounts = entry.counts.size();

const int64_t ne0 = (int64_t) entry.sums.size() / ncounts;

for (int64_t j = 0; j < ncounts; ++j) {

const float count = (float) entry.counts[j];

if (count > 0.0f) {

for (int64_t i = 0; i < ne0; ++i) {

e[j*ne0 + i] = entry.sums[j*ne0 + i] / count;

}

} else {

for (int64_t i = 0; i < ne0; ++i) {

e[j*ne0 + i] = 1;

}

if (getenv("LLAMA_TRACE")) {

float max_count = 0.0f;

for (int64_t j = 0; j < ncounts; ++j) {

const float count = (float) entry.counts[j];

if (count > max_count) {

max_count = count;

}

printf("%s: loaded data (size = %6d, n_tokens = %6d, n_chunks = %6d) for '%s'\n",

__func__, int(e.size()), int(max_count), int(max_count / loaded.chunk_size), name.c_str());

}

} else {

// Legacy format: sums contain (raw/count)*ncall, divide by ncall

const int64_t ncall = entry.counts.empty() ? 0 : entry.counts[0];

if (ncall > 0) {

for (size_t i = 0; i < entry.sums.size(); ++i) {

e[i] = entry.sums[i] / ncall;

}

} else {

for (size_t i = 0; i < entry.sums.size(); ++i) {

e[i] = entry.sums[i];

}

if (getenv("LLAMA_TRACE")) {

printf("%s: loaded data (size = %6d, ncall = %6d) for '%s'\n",

__func__, int(e.size()), int(ncall), name.c_str());

}

imatrix_datasets = std::move(loaded.datasets);

if (!imatrix_datasets.empty()) {

printf("%s: imatrix datasets=['%s'", __func__, imatrix_datasets[0].c_str());

for (size_t i = 1; i < imatrix_datasets.size(); ++i) {

printf(", '%s'", imatrix_datasets[i].c_str());

}

printf("]\n");

}

printf("%s: loaded %d importance matrix entries from %s computed on %d chunks\n", __func__, int(imatrix_data.size()), imatrix_file.c_str(), loaded.chunk_count);

return loaded.chunk_count;

}

static int prepare_imatrix(const std::string & imatrix_file,

std::vector<std::string> & imatrix_dataset,

const std::vector<std::string> & included_weights,

const std::vector<std::string> & excluded_weights,

std::unordered_map<std::string, std::vector<float>> & imatrix_data) {

int m_last_call = -1;

if (!imatrix_file.empty()) {

m_last_call = load_imatrix(imatrix_file, imatrix_dataset, imatrix_data);

}

if (imatrix_data.empty()) {

return m_last_call;

}

if (!excluded_weights.empty()) {

for (const auto & name : excluded_weights) {

for (auto it = imatrix_data.begin(); it != imatrix_data.end();) {

auto pos = it->first.find(name);

if (pos != std::string::npos) {

it = imatrix_data.erase(it);

} else {

++it;

}

if (!included_weights.empty()) {

std::unordered_map<std::string, std::vector<float>> tmp;

for (const auto & name : included_weights) {

for (auto & e : imatrix_data) {

auto pos = e.first.find(name);

if (pos != std::string::npos) {

tmp.emplace(std::move(e));

}

imatrix_data = std::move(tmp);

}

if (!imatrix_data.empty()) {

printf("%s: have %d importance matrix entries\n", __func__, int(imatrix_data.size()));

}

return m_last_call;

}

static ggml_type parse_ggml_type(const char * arg) {

for (int i = 0; i < GGML_TYPE_COUNT; ++i) {

auto type = (ggml_type)i;

const auto * name = ggml_type_name(type);

if (name && striequals(name, arg)) {

return type;

}

fprintf(stderr, "\n%s: invalid ggml_type '%s'\n\n", __func__, arg);

return GGML_TYPE_COUNT;

}

static bool parse_tensor_type(const char * data, std::vector<tensor_type_option> & tensor_type) {

const char * sep = strchr(data, '=');

if (sep == nullptr) {

printf("\n%s: malformed tensor type '%s'\n\n", __func__, data);

return false;

}

const size_t tn_len = sep - data;

if (tn_len == 0) {

printf("\n%s: missing tensor name\n\n", __func__);

return false;

}

if (const size_t qt_len = strlen(sep); qt_len == 1) {

printf("\n%s: missing quantization type\n\n", __func__);

return false;

}

std::string tn(data, tn_len);

std::transform(tn.begin(), tn.end(), tn.begin(), tolower);

sep++;

tensor_type_option tensor_type_opt;

tensor_type_opt.name = tn;

tensor_type_opt.type = parse_ggml_type(sep);

tensor_type.emplace_back(std::move(tensor_type_opt));

if (tensor_type_opt.type == GGML_TYPE_COUNT) {

printf("\n%s: invalid quantization type '%s'\n\n", __func__, sep);

return false;

}

return true;

}

static bool parse_tensor_type_file(const char * filename, std::vector<tensor_type_option> & tensor_type) {

std::ifstream file(filename);

if (!file) {

printf("\n%s: failed to open file '%s': %s\n\n", __func__, filename, std::strerror(errno));

return false;

}

std::string arg;

while (file >> arg) {

if (!parse_tensor_type(arg.c_str(), tensor_type)) {

return false;

}

return true;

}

static bool parse_layer_prune(const char * data, std::vector<int> & prune_layers) {

if (!data) {

printf("\n%s: no layer pruning ids provided\n\n", __func__);

return false;

}

const auto block_ids = string_split<std::string>(data, ',');

for (const auto & block_id : block_ids) {

int id;

try {

id = std::stoi(block_id);

} catch (...) {

id = -1;

}

if (id < 0) {

printf("\n%s: invalid layer id '%s'\n\n", __func__, block_id.c_str());

return false;

}

prune_layers.emplace_back(id);

}

sort(prune_layers.begin(), prune_layers.end());

prune_layers.erase(std::unique(prune_layers.begin(), prune_layers.end()), prune_layers.end());

return true;

}

// satisfies -Wmissing-declarations

int llama_quantize(int argc, char ** argv);

int llama_quantize(int argc, char ** argv) {

std::setlocale(LC_NUMERIC, "C");

if (argc < 3) {

usage(argv[0]);

}

llama_model_quantize_params params = llama_model_quantize_default_params();

int arg_idx = 1;

std::string imatrix_file;

std::vector<std::string> included_weights, excluded_weights;

std::vector<llama_model_kv_override> kv_overrides;

std::vector<tensor_type_option> tensor_type_opts;

std::vector<int> prune_layers;

for (; arg_idx < argc && strncmp(argv[arg_idx], "--", 2) == 0; arg_idx++) {

if (strcmp(argv[arg_idx], "--leave-output-tensor") == 0) {

params.quantize_output_tensor = false;

} else if (strcmp(argv[arg_idx], "--output-tensor-type") == 0) {

if (arg_idx < argc-1) {

params.output_tensor_type = parse_ggml_type(argv[++arg_idx]);

if (params.output_tensor_type == GGML_TYPE_COUNT) {

usage(argv[0]);

}

} else {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--token-embedding-type") == 0) {

if (arg_idx < argc-1) {

params.token_embedding_type = parse_ggml_type(argv[++arg_idx]);

if (params.token_embedding_type == GGML_TYPE_COUNT) {

usage(argv[0]);

}

} else {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--tensor-type") == 0) {

if (arg_idx == argc-1 || !parse_tensor_type(argv[++arg_idx], tensor_type_opts)) {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--tensor-type-file") == 0) {

if (arg_idx == argc-1 || !parse_tensor_type_file(argv[++arg_idx], tensor_type_opts)) {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--prune-layers") == 0) {

if (arg_idx == argc-1 || !parse_layer_prune(argv[++arg_idx], prune_layers)) {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--override-kv") == 0) {

if (arg_idx == argc-1 || !string_parse_kv_override(argv[++arg_idx], kv_overrides)) {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--dry-run") == 0) {

params.dry_run = true;

} else if (strcmp(argv[arg_idx], "--allow-requantize") == 0) {

params.allow_requantize = true;

} else if (strcmp(argv[arg_idx], "--pure") == 0) {

params.pure = true;

} else if (strcmp(argv[arg_idx], "--imatrix") == 0) {

if (arg_idx < argc-1) {

imatrix_file = argv[++arg_idx];

} else {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--include-weights") == 0) {

if (arg_idx < argc-1) {

included_weights.emplace_back(argv[++arg_idx]);

} else {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--exclude-weights") == 0) {

if (arg_idx < argc-1) {

excluded_weights.emplace_back(argv[++arg_idx]);

} else {

usage(argv[0]);

}

} else if (strcmp(argv[arg_idx], "--keep-split") == 0) {

params.keep_split = true;

} else {

usage(argv[0]);

}

if (argc - arg_idx < 2) {

printf("%s: bad arguments\n", argv[0]);

usage(argv[0]);

}

if (!included_weights.empty() && !excluded_weights.empty()) {

usage(argv[0]);

}

std::vector<std::string> imatrix_datasets;

std::unordered_map<std::string, std::vector<float>> imatrix_data;

int m_last_call = prepare_imatrix(imatrix_file, imatrix_datasets, included_weights, excluded_weights, imatrix_data);

std::vector<llama_model_imatrix_data> i_data;

std::vector<llama_model_tensor_override> t_override;

if (!imatrix_data.empty()) {

i_data.reserve(imatrix_data.size() + 1);

for (const auto & kv : imatrix_data) {

i_data.push_back({kv.first.c_str(), kv.second.data(), kv.second.size()});

}

i_data.push_back({nullptr, nullptr, 0}); // array terminator

params.imatrix = i_data.data();

{

llama_model_kv_override kvo;

std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_FILE);

kvo.tag = LLAMA_KV_OVERRIDE_TYPE_STR;

strncpy(kvo.val_str, imatrix_file.c_str(), 127);

kvo.val_str[127] = '\0';

kv_overrides.emplace_back(std::move(kvo));

}

if (!imatrix_datasets.empty()) {

llama_model_kv_override kvo;

// TODO: list multiple datasets when there are more than one

std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_DATASET);

kvo.tag = LLAMA_KV_OVERRIDE_TYPE_STR;

strncpy(kvo.val_str, imatrix_datasets[0].c_str(), 127);

kvo.val_str[127] = '\0';

kv_overrides.emplace_back(std::move(kvo));

}

{

llama_model_kv_override kvo;

std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_N_ENTRIES);

kvo.tag = LLAMA_KV_OVERRIDE_TYPE_INT;

kvo.val_i64 = imatrix_data.size();

kv_overrides.emplace_back(std::move(kvo));

}

if (m_last_call > 0) {

llama_model_kv_override kvo;

std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_N_CHUNKS);

kvo.tag = LLAMA_KV_OVERRIDE_TYPE_INT;

kvo.val_i64 = m_last_call;

kv_overrides.emplace_back(std::move(kvo));

}

if (!kv_overrides.empty()) {

kv_overrides.emplace_back();

kv_overrides.back().key[0] = 0;

params.kv_overrides = kv_overrides.data();

}

if (!tensor_type_opts.empty()) {

t_override.reserve(tensor_type_opts.size() + 1);

for (const auto & tt : tensor_type_opts) {

t_override.push_back({tt.name.c_str(), tt.type});

}

t_override.push_back({nullptr, GGML_TYPE_COUNT}); // array terminator

params.tt_overrides = t_override.data();

}

if (!prune_layers.empty()) {

prune_layers.push_back(-1); // array terminator

params.prune_layers = prune_layers.data();

}

llama_backend_init();

// parse command line arguments

const std::string fname_inp = argv[arg_idx];

arg_idx++;

std::string fname_out;

std::string ftype_str;

std::string suffix = ".gguf";

if (try_parse_ftype(argv[arg_idx], params.ftype, ftype_str)) {

// argv[arg_idx] is the ftype directly: <input> <ftype>

if (!params.dry_run) {

std::string fpath;

const size_t pos = fname_inp.find_last_of("/\\");

if (pos != std::string::npos) {

fpath = fname_inp.substr(0, pos + 1);

}

// export as [inp path]/ggml-model-[ftype]. Only add extension if there is no splitting

fname_out = fpath + "ggml-model-" + ftype_str;

if (!params.keep_split) {

fname_out += suffix;

}

arg_idx++;

if (ftype_str == "COPY") {

params.only_copy = true;

}

} else {

// argv[arg_idx] is not a valid ftype, so treat it as output path: <input> <output> <ftype>

fname_out = argv[arg_idx];

if (params.keep_split && fname_out.find(suffix) != std::string::npos) {

fname_out = fname_out.substr(0, fname_out.length() - suffix.length());

}

arg_idx++;

if (argc <= arg_idx) {

fprintf(stderr, "%s: missing ftype\n", __func__);

return 1;

}

if (!try_parse_ftype(argv[arg_idx], params.ftype, ftype_str)) {

fprintf(stderr, "%s: invalid ftype '%s'\n", __func__, argv[arg_idx]);

return 1;

}

if (ftype_str == "COPY") {

params.only_copy = true;

}

arg_idx++;

}

// parse nthreads

if (argc > arg_idx) {

try {

params.nthread = std::stoi(argv[arg_idx]);

}

catch (const std::exception & e) {

fprintf(stderr, "%s: invalid nthread '%s' (%s)\n", __func__, argv[arg_idx], e.what());

return 1;

}

if (!params.dry_run) {

if (std::error_code ec; std::filesystem::equivalent(fname_inp, fname_out, ec)) {

fprintf(stderr, "%s: error: input and output files are the same: '%s'\n", __func__, fname_inp.c_str());

return 1;

}

llama_print_build_info();

if (params.dry_run) {

fprintf(stderr, "%s: calculating quantization size for '%s' as %s", __func__, fname_inp.c_str(), ftype_str.c_str());

} else {

fprintf(stderr, "%s: quantizing '%s' to '%s' as %s", __func__, fname_inp.c_str(), fname_out.c_str(), ftype_str.c_str());

}

if (params.nthread > 0) {

fprintf(stderr, " using %d threads", params.nthread);

}

fprintf(stderr, "\n");

const int64_t t_main_start_us = llama_time_us();

int64_t t_quantize_us = 0;

// load the model

{

const int64_t t_start_us = llama_time_us();

if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), &params)) {

fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());

return 1;

}

t_quantize_us = llama_time_us() - t_start_us;

}

// report timing

{

const int64_t t_main_end_us = llama_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);

}

llama_backend_free();

return 0;

}

llama.cpp/tools/quantize/quantize.cpp at master · allozaur/llama.cpp · GitHub

Expand file tree

Breadcrumbs

quantize.cpp

Latest commit

History

Breadcrumbs

quantize.cpp

File metadata and controls