Commit Graph

Select branches

Hide Pull Requests

20250708-ci-fixes

add-chat-response-format

add-google-cloud-provider

add-quickstart-script

add-rotary-embed-tests

add-small-ttft-script

add-test-for-warmup-and-kvcache

add_L4

add_api_key

add_batch_dimension

add_chunked_atn

add_chunked_attn

add_deepseekv3

add_gptq_docs

add_integration_test

add_readme_dashboard

add_tunable_prefill

add_vlm_chunking

adding_docs

adjust-mllama-test-output

adjust-where-request-max-tokens-is-defaulted

aiter_kernels

amd-ci-fx

auto_length

automodel-supports-flash-paged-attention

avoid-cuda-graph-during-warmup-if-oom

avoid-zero-seed

backends/trtllm

backends/trtllm-executor

baichuan2-13b

bnb4

bugfix/add_tools_prompt

bugfix/moe-kernels-imports

bugfix/phi-exl2

bump-client-0.6.2

bump-kernel-versions

bump-poetry-and-requirements

chunked_attn_l4

ci-amihalik-update-chat-completion-messages

ci-new-cluster

ci-patch

ci-run-openai-function-calling-compatible-support

ci-update_xpu_image

ci-xpu

ci-xpu2

ci2

ci_amd

ci_amd2

ci_amd3

ci_amd4

close_dl_thread

compat_logger

cuda_ipc_allreduce

debug-gpt2

debug-request-id

debug-torch-23

debug/gemma2

debugging-timeouts

deploy/aml

dev

development-guide

dummy

enable-non-grammar-constrained-tools

enable-qwen2vl-video

enable-transformers-vlm

enable_non_divisible_embeddings

exl2

experiment/moe

explore-static-triton-kernels

explore-t4-gemma-issues

feat-backend-llamacpp

feat/add-load-test

feat/attention_sinks

feat/backend_abstraction

feat/backend_feature

feat/better_tokens

feat/cuda_12

feat/flash_decoding

feat/improve_max_tokens

feat/max_queue_size

feat/page_re_alloc

feat/parse_logs

feat/support_deepspeed

feature/machete

feature/moe-kernels

feature/no_repeat_ngram_size

feature/no_repeat_ngram_size_ci

feature/phi-3-small

feature/prefix

feature/radix-prefix-cache

feature/radix-prefix-cache-bench

feature/vlm-prefix-caching

fix-cudagraph-bug

fix-gemma-tokenization

fix-grammar-cleanup-bug

fix-grammar-fsm-batching

fix-mixtral-adapter-loading

fix-release-tests

fix-repack-for-marlin

fix-tool-call-def

fix-tp

fix-version-install

fix/allow-top-p-0

fix/avoid_record_streams

fix/op-trace-id

fix/parse-mamba-config

fix_default_arg

fix_exl2

fix_fp8_llama3.2

fix_leak

fix_mistral2

fix_neox_rotary_emb

fix_phi3

flashinfer

flashinfer-0.2.5

fp8_kvcache

fp8_rocm

gaudi_llama4_tmp

gha_sccache_use_secrets

git_2.0.4

git_3.1.1

git_3.2.0

git_3.2.1

git_3.3.0

git_3.3.1

git_3.3.2

git_v2.1.0

git_v2.1.1

git_v2.2.0

git_v2.3.0

git_v2.3.1

git_v2.4.0

git_v2.4.1

git_v3.0.0

git_v3.0.1

git_v3.0.2

git_v3.1.0

git_v3.2.2

git_v3.2.3

git_v3.3.3

git_v3.3.4

git_v3.3.5

improve-docs

improve-dynamic-message-content

improve-json-schema-field

improve-tool-call-and-response-ids

improve_defaults

improve_launcher_defaults

inlcude-latest-release-on-commit-builds-tags

ipex-moe

kvrouter

kvrouter-endpoints

llama-fused-compiled-mlp

main

maintenance/docker-network

maintenance/merge-vlm-input-prep

mamba2

martinigoyanes-fix-frequency-penalty

medusa

megatron

message-more-info

mi300-temp

mllama

model_compat_log

more_logs

multi-lora

new_minor_version

nix/cargo-clippy

nix/docker2

nix/pytorch-2.5.1

nix_integration_tests

nix_test2

no_root_user

no_root_user2

op-compilation-benchmarking

origin/slind_window_fix

osanseviero-patch-1

patch_version_3.3.6

pip-installable

pr-1869-ci-run

pr-2076-ci-run

pr-2290-ci-runner

pr-2366-ci-branch

pr-2444-ci-branch

pr-2517-ci-branch

pr-2711-ci-branch

pr-2784-ci-branch

pr-2840-ci-branch

pr-2954-ci-branch

pr-3002-ci-branch

pr-3004-ci-branch

pr-3018-ci-branch

precompile-kernels-workflow

prefix_chunk

prefix_default

proxy_sse_engine_state

quantization

quantization-0.1

refactor-lora-linear

release-3.2.4

remove_post_load_weights

response-header-metrics

revert

rocm-ci-build

rocm_6.2_fixes

router-grammar-compile

s3-cache

self-generating-docs

set-num-blocks

simpler_exllama

skip-mistral-test

speculative

streaming_conceptual

support-granite-vision

support-logit-bias-in-chat

support-phi-model

support-phi3-small

support-pre-compile-kernels

temp_work

test-batch-speedup-amount

test_docs

test_rocm

tmp_invariants

tmp_medusa

tmp_torch_compile

transformers-ci

triton_fix

trtllm-stop-words

trtllm/executor_stats

tuna

update-jsonschema

update_docs2

update_internal_version

update_peft

update_readme

upgrade-outlines

upgrade_mlp_speculator

use_g6

use_updated_kernels

vllm/setup

zstd

#1

#100

#101

#1010

#1018

#1019

#102

#1022

#1023

#1024

#103

#1033

#1034

#1042

#1044

#1045

#1048

#1049

#1052

#1054

#1058

#1059

#106

#1060

#1061

#1063

#1064

#1065

#1066

#1068

#107

#1070

#1071

#1075

#1076

#1077

#108

#1080

#1081

#1089

#109

#1090

#1091

#1092

#1094

#1096

#1097

#1099

#11

#110

#1100

#1101

#1102

#1103

#1105

#1110

#1112

#1116

#1123

#1128

#1134

#114

#1140

#1141

#115

#1153

#1155

#116

#1165

#1165

#117

#1173

#1176

#1178

#1179

#118

#1182

#1183

#1184

#1187

#119

#1198

#1202

#1211

#1214

#1219

#122

#1224

#1228

#123

#1239

#1241

#1242

#1243

#1246

#1252

#126

#1260

#1267

#1270

#1272

#1274

#1276

#1279

#128

#1285

#1287

#129

#1294

#1295

#13

#130

#1301

#1305

#1307

#1308

#1313

#132

#1326

#1328

#133

#1336

#1337

#134

#1341

#1343

#1346

#1347

#1348

#135

#1351

#1352

#1353

#1358

#136

#1361

#1364

#137

#1370

#1373

#138

#1381

#1386

#139

#1390

#1395

#14

#140

#1408

#141

#1414

#1419

#142

#1420

#1424

#1425

#1427

#1428

#143

#1436

#144

#1442

#1448

#145

#1450

#1453

#1454

#1455

#1459

#1461

#1462

#1463

#1469

#147

#1470

#1471

#1473

#1475

#1476

#1477

#1478

#148

#1480

#1484

#1486

#1488

#1489

#149

#1490

#1491

#1492

#1494

#1495

#1496

#1497

#1498

#15

#150

#1502

#1504

#1505

#1506

#151

#1511

#1512

#1514

#1515

#1516

#1517

#1518

#152

#1520

#1523

#1524

#1526

#1527

#153

#1532

#1533

#1537

#1539

#154

#1540

#1541

#1542

#1543

#155

#1550

#1552

#1555

#1556

#1557

#1560

#1563

#1564

#1567

#1568

#1569

#1570

#1571

#1576

#1577

#1578

#1579

#1580

#1583

#1584

#1585

#1586

#1587

#1588

#159

#1591

#1592

#1594

#16

#160

#1603

#1605

#1606

#1607

#1608

#1609

#161

#1610

#1614

#1617

#1618

#1619

#162

#1621

#1626

#1628

#163

#1632

#1637

#1638

#1639

#164

#1646

#1648

#1650

#1651

#1653

#1658

#1660

#1662

#1663

#1664

#1666

#1667

#1668

#167

#1676

#168

#1682

#1685

#1686

#1693

#1697

#1698

#17

#170

#1702

#1703

#1704

#1707

#1708

#1709

#1710

#1713

#1714

#1715

#1716

#1718

#1719

#1726

#1727

#1729

#173

#1730

#1731

#1734

#1735

#1736

#1737

#1739

#174

#1740

#1747

#1748

#1749

#175

#1751

#1755

#1756

#1758

#1759

#1760

#1764

#1765

#1767

#1768

#1773

#1774

#1775

#178

#1784

#1789

#179

#1790

#1791

#1797

#1798

#18

#180

#1800

#1801

#1808

#181

#1811

#1812

#1813

#1815

#1816

#1817

#1818

#1820

#1825

#1827

#1828

#1829

#183

#1830

#1832

#1833

#1835

#1836

#1839

#184

#1840

#1841

#1843

#1844

#1845

#1848

#1849

#185

#1850

#1851

#1854

#1855

#186

#1860

#1865

#1866

#1869

#187

#1882

#1884

#1886

#1888

#1889

#1890

#1892

#1894

#1895

#1898

#19

#190

#1902

#1906

#1908

#1909

#191

#1910

#1912

#1915

#1916

#1917

#1918

#1919

#1920

#1921

#1923

#1924

#1925

#1929

#193

#1931

#1932

#1934

#1935

#1936

#1937

#1938

#1939

#194

#1940

#1942

#1947

#1948

#1949

#1950

#1951

#1953

#1954

#1958

#1959

#196

#1963

#1965

#1967

#1970

#1971

#1975

#1980

#1981

#1985

#1986

#1988

#1989

#1990

#1994

#1995

#1996

#2

#20

#200

#2002

#2003

#2004

#2005

#2006

#2008

#201

#2010

#2011

#2013

#2014

#2015

#2016

#2017

#202

#2020

#2021

#2022

#2023

#2024

#2028

#203

#2031

#2032

#2033

#2034

#2038

#2039

#2044

#2045

#2046

#2047

#2049

#205

#2050

#2052

#2054

#2059

#2060

#2061

#2062

#2063

#2065

#2066

#2068

#207

#2071

#2072

#2074

#2075

#2076

#2078

#2079

#208

#2080

#2084

#2085

#2086

#2087

#2088

#2089

#2091

#2092

#2094

#2095

#2097

#2099

#210

#2101

#2102

#2103

#2104

#2105

#2109

#2110

#2111

#2114

#2115

#2116

#2117

#2118

#2119

#212

#2120

#2123

#2124

#2125

#2127

#2128

#2129

#213

#2131

#2132

#2133

#2134

#2135

#2137

#2138

#214

#2140

#2141

#2142

#2148

#2149

#215

#2151

#2152

#2153

#2155

#2156

#2158

#216

#2161

#2163

#2164

#2165

#2166

#2167

#2168

#2169

#217

#2170

#2173

#2175

#2176

#2178

#2179

#218

#2180

#2181

#2182

#2186

#2187

#2189

#219

#2190

#2191

#2193

#2194

#2196

#22

#220

#2201

#2202

#2203

#2204

#2205

#2208

#2209

#221

#2212

#2213

#2215

#2216

#2217

#222

#2220

#2221

#2224

#2225

#2226

#2228

#2230

#2231

#2232

#2233

#2237

#2242

#2243

#2244

#2245

#2248

#2249

#2250

#2251

#2254

#2255

#2256

#2257

#2258

#2259

#226

#2260

#2261

#2262

#2266

#2268

#2269

#227

#2271

#2272

#2273

#2274

#2276

#2277

#2278

#2279

#228

#2281

#2282

#2283

#2284

#2285

#2286

#2287

#2288

#2289

#2290

#2291

#2292

#2298

#2299

#23

#2300

#2303

#2304

#2306

#2307

#2308

#2309

#2311

#2311

#2313

#2314

#2315

#2317

#2320

#2323

#2325

#2326

#2327

#2328

#2329

#233

#2330

#2331

#2333

#2335

#2336

#2337

#2338

#2339

#234

#2341

#2342

#2343

#2344

#2345

#2346

#2347

#235

#2350

#2351

#2352

#2353

#2354

#2357

#2358

#2359

#2360

#2361

#2364

#2365

#2366

#2367

#2368

#237

#2370

#2371

#2372

#2374

#2377

#2378

#2379

#2381

#2382

#2384

#2385

#2386

#2387

#2389

#2390

#2391

#2392

#2394

#2395

#2396

#2397

#2398

#2399

#24

#2401

#2402

#2403

#2404

#2405

#2406

#2407

#2408

#2410

#2411

#2412

#2414

#2415

#2416

#2419

#242

#2420

#2422

#2423

#2424

#2426

#2427

#2428

#2429

#2430

#2431

#2433

#2437

#2438

#2439

#244

#2442

#2443

#2444

#2449

#2450

#2451

#2453

#2454

#2455

#2459

#246

#2462

#2463

#2468

#2469

#2470

#2471

#2472

#2473

#2477

#2478

#2479

#248

#2481

#2482

#2484

#2486

#2489

#2490

#2491

#2492

#2493

#2494

#2496

#2497

#2498

#2499

#25

#250

#2500

#2501

#2507

#251

#2510

#2511

#2512

#2513

#2514

#2515

#2516

#2517

#2518

#2519

#252

#2520

#2521

#2524

#2525

#2527

#2528

#2529

#2532

#2533

#2535

#2536

#2537

#2538

#2539

#2540

#2545

#2546

#2547

#2548

#255

#2550

#2551

#2552

#2553

#2554

#2555

#2556

#2557

#2558

#2561

#2562

#2563

#2566

#2567

#2568

#257

#2574

#2575

#2577

#2578

#2579

#258

#2580

#2582

#2585

#2586

#2587

#2588

#2589

#259

#2590

#2591

#2592

#2594

#2595

#2596

#2597

#2599

#26

#2600

#2601

#2602

#2603

#2604

#2605

#2606

#2607

#2609

#261

#2610

#2611

#2612

#2614

#2616

#2617

#2619

#262

#2620

#2622

#2623

#2625

#2627

#2628

#2629

#2630

#2631

#2632

#2633

#2634

#2637

#264

#2640

#2642

#2642

#2645

#2646

#2647

#2648

#2650

#2651

#2652

#2655

#2658

#2659

#266

#2661

#2663

#2664

#2665

#2666

#2668

#267

#2673

#2674

#2677

#2678

#2680

#2682

#2683

#2684

#2685

#2686

#2687

#2688

#2689

#269

#2690

#2691

#2692

#2693

#2694

#2695

#2697

#2698

#2699

#27

#2701

#2702

#2704

#2706

#2707

#2708

#2709

#2710

#2711

#2712

#2713

#2714

#2716

#2717

#2718

#2719

#272

#2720

#2721

#2723

#2724

#2725

#2726

#2732

#2733

#2738

#274

#2740

#2741

#2742

#2743

#2745

#2746

#275

#2750

#2751

#2753

#2754

#2755

#2756

#2756

#2758

#276

#2760

#2761

#2762

#2764

#2765

#2766

#2767

#2768

#2769

#277

#2770

#2771

#2772

#2773

#2774

#2777

#2778

#2779

#278

#2782

#2784

#2785

#2786

#2788

#2789

#2790

#2791

#2792

#2793

#2795

#2796

#2797

#2798

#2799

#28

#2802

#2803

#2806

#2807

#2808

#2809

#2810

#2811

#2812

#2814

#2815

#2816

#2817

#2818

#282

#2824

#2825

#2826

#2827

#2829

#2831

#2833

#2834

#2837

#284

#2840

#2841

#2845

#2846

#2848

#2848

#2849

#285

#2850

#2852

#2855

#2856

#2858

#2859

#286

#2861

#2862

#2863

#2866

#2866

#287

#2870

#2874

#2874

#2878

#2882

#2883

#2884

#2885

#2886

#2891

#2892

#2893

#2898

#29

#2901

#2903

#2904

#2905

#2907

#2908

#2910

#2911

#2912

#2913

#2916

#2917

#2918

#2919

#292

#2921

#2922

#2924

#2928

#2929

#2931

#2932

#2933

#2935

#2936

#2937

#2938

#294

#2940

#2941

#2942

#2943

#2945

#2947

#2948

#2949

#2950

#2951

#2953

#2954

#2957

#2958

#2960

#2961

#2962

#2963

#2964

#2964

#2965

#2965

#2966

#2967

#2968

#297

#2970

#2971

#2972

#2975

#2976

#2976

#2977

#2979

#298

#2980

#2981

#2982

#2983

#2988

#299

#2990

#2991

#2992

#2993

#2995

#2996

#2998

#2999

#30

#3000

#3001

#3002

#3003

#3004

#3006

#3007

#3008

#3010

#3012

#3012

#3013

#3015

#3016

#3017

#3018

#302

#3021

#3022

#3024

#3027

#3028

#3029

#303

#3030

#3031

#3032

#3033

#3034

#3034

#3035

#3036

#3037

#3039

#304

#3040

#3041

#3042

#3044

#3045

#3046

#3047

#3048

#3049

#305

#3051

#3053

#3054

#3055

#3056

#3057

#3060

#3061

#3063

#3063

#3064

#3064

#3065

#3065

#3067

#3068

#3069

#3072

#3073

#3074

#3075

#3076

#3077

#3078

#3079

#3079

#308

#3080

#3081

#3083

#3084

#3085

#3086

#3089

#3091

#3092

#3093

#3094

#3095

#3096

#3098

#3099

#31

#310

#3100

#3101

#3103

#3106

#3107

#3108

#3109

#3111

#3111

#3112

#3113

#3116

#3117

#3118

#3120

#3121

#3122

#3124

#3125

#3126

#3127

#3128

#3129

#313

#3131

#3132

#3134

#3136

#3141

#3142

#3144

#3145

#3147

#3148

#3150

#3151

#3152

#3154

#3154

#3156

#3157

#3160

#3161

#3162

#3162

#3164

#3164

#3166

#3166

#3167

#317

#3170

#3171

#3172

#3174

#3176

#3179

#318

#3182

#3184

#3186

#3186

#3187

#3188

#3189

#3193

#3194

#3194

#3196

#3197

#3197

#32

#3200

#3201

#3201

#3202

#3204

#3206

#3207

#3210

#3210

#3211

#3217

#3218

#3220

#3221

#3222

#3223

#3224

#3229

#3230

#3231

#3231

#3232

#3234

#3235

#3236

#3237

#3238

#3239

#3240

#3242

#3244

#3245

#3246

#3249

#325

#3252

#3253

#3254

#3255

#3255

#3256

#3258

#3260

#3261

#3262

#3263

#3264

#3265

#3266

#3266

#3267

#3268

#3269

#327

#3270

#3271

#3273

#3274

#3276

#3276

#328

#3280

#3281

#3282

#3283

#3284

#3286

#3287

#3288

#3288

#329

#3291

#3291

#3292

#3292

#3297

#3298

#33

#3300

#3300

#3302

#3302

#3308

#3310

#3310

#3311

#3312

#3313

#3314

#3315

#3315

#3319

#3322

#3323

#3324

#3325

#3326

#3327

#334

#335

#336

#34

#340

#341

#343

#344

#348

#35

#351

#352

#353

#356

#357

#358

#359

#36

#360

#362

#363

#364

#367

#368

#37

#370

#373

#379

#384

#385

#388

#39

#393

#394

#395

#396

#4

#40

#400

#404

#406

#407

#41

#411

#412

#42

#434

#438

#44

#441

#443

#45

#453

#46

#462

#465

#47

#470

#472

#475

#477

#48

#480

#483

#485

#488

#49

#498

#5

#50

#501

#502

#51

#513

#514

#516

#519

#52

#520

#521

#522

#525

#529

#53

#534

#54

#543

#544

#545

#55

#550

#553

#557

#558

#56

#561

#562

#567

#57

#575

#578

#579

#58

#580

#581

#582

#583

#585

#586

#587

#588

#59

#590

#595

#596

#6

#60

#600

#605

#608

#609

#61

#611

#616

#617

#618

#619

#62

#621

#623

#624

#626

#63

#630

#633

#634

#635

#639

#64

#642

#643

#647

#648

#659

#66

#661

#664

#665

#666

#67

#670

#671

#678

#68

#684

#689

#698

#7

#70

#704

#708

#71

#712

#713

#715

#719

#72

#721

#723

#725

#727

#73

#733

#737

#738

#740

#741

#743

#745

#746

#748

#75

#750

#76

#761

#762

#767

#768

#770

#773

#783

#785

#789

#791

#793

#794

#795

#797

#798

#799

#8

#803

#805

#806

#809

#810

#812

#82

#820

#821

#822

#823

#829

#831

#836

#838

#84

#842

#848

#85

#851

#852

#853

#854

#858

#86

#860

#862

#867

#868

#87

#872

#88

#881

#884

#886

#889

#89

#892

#893

#898

#9

#90

#900

#901

#905

#906

#91

#910

#911

#918

#921

#93

#930

#932

#935

#94

#941

#947

#95

#950

#951

#953

#954

#957

#958

#96

#963

#964

#966

#968

#97

#971

#977

#981

#986

#989

#990

#993

#994

#999

v0.2.0

v0.2.1

v0.3.0

v0.3.1

v0.3.2

v0.4.0

v0.4.1

v0.4.2

v0.4.3

v0.5.0

v0.6.0

v0.7.0

v0.8.0

v0.8.1

v0.8.2

v0.9.0

v0.9.1

v0.9.2

v0.9.3

v0.9.4

v1.0.0

v1.0.1

v1.0.2

v1.0.3

v1.1.0

v1.1.1

v1.2.0

v1.3.0

v1.3.1

v1.3.2

v1.3.3

v1.3.4

v1.4.0

v1.4.1

v1.4.2

v1.4.3

v1.4.4

v1.4.5

v2.0.0

v2.0.1

v2.0.2

v2.0.3

v2.0.4

v2.1.0

v2.1.1

v2.2.0

v2.3.0

v2.3.1

v2.4.0

v2.4.1

v3.0.0

v3.0.1

v3.0.2

v3.1.0

v3.1.1

v3.2.0

v3.2.1

v3.2.2

v3.2.3

v3.3.0

v3.3.1

v3.3.2

v3.3.3

v3.3.4

v3.3.5

Mono Color

• 1c917c0349 fix: run lint and update docs drbh 2024-09-02 19:29:27 +0000
• 1fb9d406e7 feat: return reasonable generation and add integration test drbh 2024-09-02 19:20:49 +0000
• dff1b9f795 fix: prefer llama base model and improve rotary logic drbh 2024-09-02 16:19:45 +0000
• 853bc514f2 feat: support phi3.5 moe model loading drbh 2024-08-30 15:14:59 +0000
• 5a08c33696 Add support for GPTQ-quantized MoE models using MoE Marlin Daniël de Kok 2024-09-24 11:24:09 +0000
• e790cfc0e4
  Update architecture.md (#2577) Ikram Ul Haq 2024-09-30 09:56:20 +0300
• afc7ded84f
  Remove compute capability lazy cell (#2580) Daniël de Kok 2024-09-30 08:48:47 +0200
• 2401fdc889 cleaned dockerfile Mohit Sharma 2024-09-30 03:40:00 +0000
• 513ba5a0b4 feat(tgi_common) continue more utility functions cuda_ipc_allreduce Morgan Funtowicz 2024-09-29 12:33:31 +0000
• 0b80a928eb Don't spam journalctl on Linux Daniël de Kok 2024-09-29 12:43:55 +0200
• b806a856c7 Stream to make the builder image smaller Daniël de Kok 2024-09-29 12:35:56 +0200
• fb81ffce02 feat(common) adding device utilities EC2 Default User 2024-09-28 21:10:18 +0000
• 755361b932 Example of building the Docker image using Nix inside Docker Daniël de Kok 2024-09-28 21:10:33 +0200
• 1028996fb3
  flashinfer: pass window size and dtype (#2574) Daniël de Kok 2024-09-28 18:41:41 +0200
• 3b28cf9067 improve dockerfile Mohit Sharma 2024-09-28 15:54:45 +0000
• 6d9515578f break when there's nothing to read Wang, Yi A 2024-09-27 18:35:39 -0700
• 77a36d45eb nix: experimental support for building a Docker image Daniël de Kok 2024-08-29 08:16:37 +0000
• 5f9120da9c feat(tgi_common): add initial set of common functions for reuse Morgan Funtowicz 2024-09-27 18:53:56 +0200
• 7cb49f6f4f float16 dep Mohit Sharma 2024-09-27 15:53:44 +0000
• b2cd1b66ed fix imports after rebase Mohit Sharma 2024-09-27 15:52:43 +0000
• 473d9a892d Merge remote-tracking branch 'upstream/main' into rocm_6.2_updates Mohit Sharma 2024-09-27 15:36:12 +0000
• cdda9dcb28 Remove compute capability lock Daniël de Kok 2024-09-27 14:22:46 +0000
• 5b6b74e21d
  Improve support for GPUs with capability < 8 (#2575) Daniël de Kok 2024-09-27 16:19:42 +0200
• 346dfe398a remove import Mohit Sharma 2024-09-27 12:59:35 +0000
• a24c2cc5e9 updated default value Mohit Sharma 2024-09-27 12:39:12 +0000
• ac2dccd174 improved error messag Mohit Sharma 2024-09-27 12:34:04 +0000
• 816d4b67b2 fix import Mohit Sharma 2024-09-27 12:32:17 +0000
• 3eb68a371d Capability as usizes Daniël de Kok 2024-09-27 11:42:17 +0000
• a29636ee0a Move disabling prefix caching into the block of exceptions Daniël de Kok 2024-09-27 11:29:36 +0000
• 47c81d2924 Merge remote-tracking branch 'upstream/main' into fix_rocm_fa Mohit Sharma 2024-09-27 10:34:16 +0000
• 829144d15a addressed review comments Mohit Sharma 2024-09-27 10:28:37 +0000
• 31a6065fac Add some utility functions in tgiccl for now Morgan Funtowicz 2024-09-26 23:31:07 +0200
• 105f384461 Merge branch 'cuda_ipc_allreduce' of github.com:huggingface/text-generation-inference into cuda_ipc_allreduce Morgan Funtowicz 2024-09-26 23:52:40 +0200
• 45e060e857 feat: propagate max_concurrent_requests to queue state entries instead of hardcoded 128 in backends/v3 Venkat Raman 2024-09-26 19:51:10 +0200
• 77ddc8309d feat: propagate max_concurrent_requests to queue state entries instead of hardcoded 128 in backend/v2 Venkat Raman 2024-09-26 18:02:42 +0200
• 36f418bd04
  Update architecture.md Ikram Ul Haq 2024-09-26 18:40:41 +0300
• 8c0f9312f3 nix: add flash-attn-v1 to the server environment Daniël de Kok 2024-09-26 13:34:01 +0000
• bee5ee1f03 Improve support for GPUs with capability < 8 Daniël de Kok 2024-09-26 13:35:27 +0000
• cdca095012 flashinfer: pass window size and dtype Daniël de Kok 2024-09-26 12:59:51 +0000
• 0aa66d693a
  Fix build with --features google (#2566) Alvaro Bartolome 2024-09-26 11:41:38 +0200
• ecbf34b280
  Add cargo test --features google Alvaro Bartolome 2024-09-26 11:19:32 +0200
• 0b7df77178
  Add LoRA adapters support for Gemma2 (#2567) Alvaro Bartolome 2024-09-26 10:54:08 +0200
• bab529c916 Make Gaudi adapt to the tgi 2.3.0 yuanwu 2024-09-26 01:53:52 +0000
• de38bf2664
  Updating Cargo lock mllama Nicolas Patry 2024-09-25 20:51:29 +0200
• 28f369cc99
  Ugrade transformers 4.45 Nicolas Patry 2024-09-25 20:46:44 +0200
• 31a4c24f74
  Mllama Nicolas Patry 2024-09-25 20:41:40 +0200
• 44cdb00bbb
  Updating config, removing TODO Nicolas Patry 2024-09-25 10:48:03 +0200
• 047e2e8163
  Fix idefics. Nicolas Patry 2024-09-23 16:13:22 +0200
• f1f9079ec6
  Cleaner condition. Nicolas Patry 2024-09-23 15:50:43 +0200
• 8abdd08ef4
  Working state ? (Broke idefics1 temporarily). Nicolas Patry 2024-09-23 15:25:26 +0200
• 39d2073e93
  Preprocessing. Nicolas Patry 2024-09-18 17:59:13 +0200
• 907906466a
  Working loading state. Nicolas Patry 2024-09-18 17:01:36 +0200
• fb28d374e1
  Make black formatting happy Alvaro Bartolome 2024-09-25 19:10:10 +0200
• e424752fa3
  Enable the AutoGPTQ (#217) yuanwu2017 2024-09-26 00:55:02 +0800
• 3b7e010a4c
  Add LoRA adapters support for Gemma2 Alvaro Bartolome 2024-09-25 18:12:12 +0200
• b49d88a970
  Fix cargo build --features google Alvaro Bartolome 2024-09-25 17:15:23 +0200
• f1c6eacd75 feat(tgiccl): initial commit for custom tgiccl backend Morgan Funtowicz 2024-09-25 12:27:28 +0000
• 14fdc4ae5e Add some missing modification of 2.3.0 because of conflict yuanwu 2024-09-25 07:49:49 +0000
• 514a5a737d Preparing for release. (#2540) Nicolas Patry 2024-09-20 17:42:04 +0200
• bd9675c8c7 fix: wrap python basic logs in debug assertion in launcher (#2539) OlivierDehaene 2024-09-20 16:59:31 +0200
• 3519398a14 hotfix: ipex fails since cuda moe kernel is not supported (#2532) Wang, Yi 2024-09-20 16:02:55 +0800
• b6ef2bfc1b doc: clarify that --quantize is not needed for pre-quantized models (#2536) Daniël de Kok 2024-09-19 22:17:15 +0200
• c1a99e2f15 Update to moe-kenels 0.3.1 (#2535) Daniël de Kok 2024-09-19 22:16:32 +0200
• 2d470c8282 Stream options. (#2533) Nicolas Patry 2024-09-19 20:50:37 +0200
• 29a93b78ba Move to moe-kernels package and switch to common MoE layer (#2511) Daniël de Kok 2024-09-17 18:08:58 +0200
• 88b72c8eb3 fix: metrics unbounded memory (#2528) OlivierDehaene 2024-09-17 18:01:28 +0200
• 0ecbd61099 nix: pure Rust check/fmt/clippy/test (#2525) Daniël de Kok 2024-09-17 12:14:30 +0200
• 0110b83aff Adding a test for FD. (#2516) Nicolas Patry 2024-09-16 17:00:54 +0200
• e8c329372b Add tests for Mixtral (#2520) Daniël de Kok 2024-09-16 12:39:18 +0200
• afe5cae8fc Use ratatui not (deprecated) tui (#2521) Alex Strick van Linschoten 2024-09-13 18:45:28 +0200
• cbfe9e5185 hotfix : enable intel ipex cpu and xpu in python3.11 (#2517) Wang, Yi 2024-09-12 23:23:49 +0800
• 5fc0e0c589 fix: pass missing revision arg for lora adapter when loading multiple… (#2510) drbh 2024-09-12 17:04:52 +0200
• 7d897188d5 Add nix test. (#2513) Nicolas Patry 2024-09-12 14:54:56 +0200
• 7be7ab7015 nix: support Python tokenizer conversion in the router (#2515) Daniël de Kok 2024-09-12 10:44:01 +0200
• f32fa568b6 Fix truffle (#2514) Nicolas Patry 2024-09-11 22:45:19 +0200
• c6b568b892 Fix tokenization yi (#2507) Nicolas Patry 2024-09-11 22:41:56 +0200
• 510d1c76c8 Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) Nicolas Patry 2024-09-11 18:10:40 +0200
• b67a0cd37b Add Directory Check to Prevent Redundant Cloning in Build Process (#2486) Vallepu Vamsi Krishna 2024-09-07 16:49:43 +0530
• eb54d956ef Fixing more correctly the invalid drop of the batch. (#2498) Nicolas Patry 2024-09-06 17:35:49 +0200
• 7c2ed55b2e Add links to Adyen blogpost (#2500) Martin Iglesias Goyanes 2024-09-06 17:00:54 +0200
• 0198db125e hotfix: add syrupy to the right subproject (#2499) Daniël de Kok 2024-09-06 12:47:06 +0200
• 67f44cce0d radix trie: add assertions (#2491) Daniël de Kok 2024-09-06 11:55:23 +0200
• 8ba790a14e Fix incompatibility with latest syrupy and update in Poetry (#2497) Daniël de Kok 2024-09-06 11:00:52 +0200
• 1e14a94721 nix: add pyright/ruff for proper LSP in the impure devshell (#2496) Daniël de Kok 2024-09-06 10:19:04 +0200
• 938a7f3c3a hotfix: fix regression of attention api change in intel platform (#2439) Wang, Yi 2024-09-05 23:41:39 +0800
• d8610a6219 Add two handy gitignores for Nix environments (#2484) Daniël de Kok 2024-09-05 17:06:54 +0200
• 556a87030b Adding links to Adyen blogpost. (#2492) Nicolas Patry 2024-09-05 16:11:52 +0200
• c7b495f97d hotfix: avoid non-prefilled block use when using prefix caching (#2489) Daniël de Kok 2024-09-05 15:09:29 +0200
• 34a6399a50 feat: support lora revisions and qkv_proj weights (#2482) drbh 2024-09-02 13:09:06 -0400
• be5cb0cf7f fix: enable chat requests in vertex endpoint (#2481) drbh 2024-09-02 10:00:52 -0400
• 3e17cb7866 nix: add punica-kernels (#2477) Daniël de Kok 2024-09-02 11:31:36 +0200
• 07c70e7840 nix: improve impure devshell (#2478) Daniël de Kok 2024-09-02 09:27:10 +0200
• a313355d2b Tied embeddings in MLP speculator. (#2473) Nicolas Patry 2024-08-29 17:44:54 +0200
• 61b2f493a8 update doc with intel cpu part (#2420) Wang, Yi 2024-08-29 23:42:02 +0800
• 990478b285 feat: add /v1/models endpoint (#2433) drbh 2024-08-29 10:32:38 -0400
• 4e1ca8d7bd Lots of improvements (Still 2 allocators) (#2449) Nicolas Patry 2024-08-29 16:29:01 +0200
• 622c9c367a nix: build Torch against MKL and various other improvements (#2469) Daniël de Kok 2024-08-29 16:25:25 +0200
• 08834e0cfd fix: improve regex expression (#2468) drbh 2024-08-28 13:44:44 -0400
• e80b2c21dc fix: bump minijinja version and add test for llama 3.1 tools (#2463) drbh 2024-08-27 13:31:08 -0400
• 6793b720ba Fixing CI. (#2462) Nicolas Patry 2024-08-27 15:33:02 +0200