Commit Graph

Select branches

Hide Pull Requests

ErvinXie-patch-1

JimmyPeilinLi-patch-1

JimmyPeilinLi-patch-2

add-maintainers

archive-kt-sft

auto/sync-sglang

avx2

bump-sglang-pr31

chore/kt-layerwise-prefill-label

chore/kt-layerwise-prefill-main

chore/kt-run-numa-nodes-unified

ci/four-main-pypi-release

ci/model-e2e-acceptance

cli-dev-ljq

cpu-fix

debug_llama

doc-reorg-entrypoints-support-matrix

docs-v061-refresh

docs/deepseek-v4-flash-docker

docs/gosim-2026-and-roadmap-link

docs/kt-ft-figure2-single-column-20261010

docs/kt-ft-paper-20261008

experts_sched

feat/mistral-loader-support

fix-deploy-djw

fix-docker-build

fix-import

fix/avx2-wheel-feature-isolation

fix/glm53-index-share-sync

fix/release-self-hosted-runner

fix/sglang-kt-detection

flatten-ktransformers-shim

fp4-moe-amx

gh-pages

glm47_fp8

hotfix/0.7.0.post2-pypi-runtime

kimi_k2.5

ksft-llama

ksft-sglang

kt-kernel-torch-range-v061

layerwise-prefill-opt

ljq-cli-dev

ljq-cli-dev-new

ljq-dev-1

lut-nvfp4

main

minimax-m2.5

mtp

oql-dev

oql-doc

ovowei-patch-1

ovowei-patch-2

ovowei-patch-3

perf/bf16-grad-norm-20261010

qwen3.5

refactor_sft

refactor_sft_int4_debug

release/0.7.0.post2-frozen-pypi

release/0.7.0.post3-frozen-pypi

release/20260911-carrier-repair

release/20260911-ci-python

release/20260911-pypi

release/automate-kt-sft-pypi

release/v0.5.3

revert-1918-fix/rocm-cpuinfer-stream-bridge

route-moe

sft

sft-rel

sft-whl

sosp25-ae

support-glm5-next-djw

support-glm51-djw

support-glm52-djw

#1005

#1013

#1015

#1024

#1027

#1029

#1030

#1031

#1033

#1034

#1042

#1043

#1044

#1049

#106

#1060

#1063

#1064

#1069

#1079

#1084

#1085

#1090

#1091

#1095

#1096

#1097

#1098

#1099

#110

#1100

#1101

#1103

#1108

#1109

#1116

#1132

#1134

#1135

#1137

#1143

#115

#1154

#1157

#1158

#1159

#1160

#1163

#1165

#1167

#1168

#1170

#1172

#1177

#118

#1180

#1182

#1183

#1184

#1186

#1188

#1193

#1197

#1198

#1202

#1204

#1210

#1211

#1212

#1215

#1216

#1217

#1218

#1219

#122

#1220

#1221

#1222

#1223

#1224

#1225

#1227

#123

#124

#1241

#1244

#1245

#1246

#1247

#126

#1266

#127

#1270

#1271

#1276

#1277

#128

#1280

#1289

#1295

#1296

#1297

#1298

#1300

#1301

#1303

#1304

#1305

#1306

#1307

#1311

#1313

#1320

#1323

#1328

#1331

#1337

#1342

#1343

#135

#1350

#1351

#1358

#1361

#1366

#1372

#1379

#1398

#1399

#14

#1405

#1407

#1409

#141

#1410

#142

#1422

#1428

#143

#1431

#1432

#1434

#1435

#1436

#1437

#1438

#1439

#144

#1449

#1452

#1456

#1457

#1458

#1458

#1466

#1487

#1493

#1494

#1495

#1498

#1500

#1505

#1506

#151

#152

#1520

#1521

#1522

#1523

#1525

#1527

#1529

#153

#1530

#1531

#1535

#1538

#1540

#1542

#1543

#1545

#1547

#1548

#1549

#1550

#1551

#1552

#1554

#1557

#1558

#1559

#1560

#1561

#1562

#1564

#1568

#1569

#1571

#1572

#1573

#1574

#1576

#158

#1581

#1583

#1584

#1585

#1586

#1587

#1588

#1589

#1590

#1592

#1594

#1595

#1596

#1597

#1599

#160

#1600

#1602

#1603

#1604

#1606

#1607

#1609

#1613

#1614

#1615

#1616

#1617

#1619

#1621

#1622

#1623

#1624

#1625

#1626

#1629

#163

#1630

#1631

#1632

#1634

#1636

#1638

#1640

#1642

#1643

#1644

#1646

#1647

#1648

#165

#1653

#1656

#1659

#166

#1660

#1662

#1663

#1668

#1669

#1670

#1671

#1672

#1673

#1674

#1675

#1683

#1684

#1685

#1686

#1687

#1691

#1695

#1696

#1698

#1699

#17

#170

#1702

#1703

#1704

#1706

#1707

#1708

#1712

#1716

#1717

#1718

#1719

#1720

#1721

#1722

#1723

#1724

#1725

#1726

#1728

#1729

#1731

#1733

#1734

#1735

#1737

#1738

#1739

#1740

#1742

#1743

#1744

#1745

#1746

#1748

#1749

#1752

#1763

#1764

#1765

#1766

#1768

#1769

#1770

#1771

#1772

#178

#1780

#1783

#1784

#1788

#1789

#1791

#1796

#1797

#1798

#1799

#18

#180

#1800

#1801

#1802

#1805

#1807

#1808

#1810

#1811

#1812

#1814

#1819

#1821

#1822

#1823

#1824

#1825

#1828

#183

#1830

#1833

#1834

#1837

#1838

#1840

#1844

#1845

#1846

#1848

#1849

#1850

#1851

#1853

#1857

#1862

#1872

#1873

#1875

#1876

#1886

#1887

#189

#1890

#1891

#1892

#1899

#190

#1900

#1901

#1902

#1903

#1904

#1906

#1908

#1909

#1916

#1918

#1919

#1920

#1923

#1925

#1926

#1927

#1929

#1932

#1934

#1935

#1936

#1937

#1941

#1942

#1944

#1945

#1948

#1950

#1952

#1953

#1954

#1955

#1957

#1958

#1959

#1962

#1963

#1964

#1965

#1966

#1967

#1970

#1972

#1973

#1974

#1975

#1976

#1979

#1980

#1984

#1986

#1987

#1991

#1993

#1994

#1995

#1997

#2

#200

#2003

#2003

#2005

#2006

#2010

#2014

#2015

#2018

#2020

#2020

#2021

#2022

#2025

#2026

#2028

#2029

#2031

#2032

#2033

#2037

#2041

#2043

#2043

#2044

#2046

#2047

#2048

#2049

#2051

#2052

#2054

#2055

#2057

#2059

#2062

#2063

#2064

#2064

#2068

#2069

#2070

#2071

#2074

#2075

#2079

#2080

#2082

#2085

#2085

#2086

#2088

#2089

#2091

#2092

#2093

#2093

#2094

#2095

#2095

#2096

#2096

#2097

#2097

#2101

#2101

#2102

#2102

#2103

#2103

#2104

#2105

#2111

#2111

#2112

#2114

#2116

#2117

#2119

#2119

#2120

#2120

#2121

#2121

#2122

#2122

#2123

#2123

#2124

#2124

#2125

#2125

#2126

#2126

#2129

#2129

#2130

#2130

#2131

#2131

#2132

#2132

#2133

#2133

#2134

#2134

#2135

#2135

#2136

#2137

#2137

#2138

#2138

#2140

#2141

#2142

#2142

#2152

#2153

#2153

#2154

#2155

#2155

#2156

#2157

#2158

#2159

#2160

#2161

#2161

#2162

#2163

#2164

#2165

#2166

#2167

#2168

#2168

#2169

#2170

#2171

#2173

#2174

#2174

#2175

#2176

#2177

#2180

#2181

#2182

#2185

#2186

#2187

#2188

#2190

#2190

#2191

#2193

#2193

#2194

#2195

#2196

#2197

#2198

#2199

#220

#2200

#2201

#2201

#2202

#2203

#2204

#2205

#2206

#2207

#2209

#2210

#2211

#2212

#2212

#2215

#2215

#2216

#2217

#2217

#2219

#2219

#2220

#2223

#2224

#2225

#2228

#2229

#2229

#2231

#2231

#2232

#2233

#2234

#2235

#2236

#2236

#2237

#2237

#2238

#2238

#2239

#2239

#224

#2240

#2240

#2241

#2241

#2242

#2242

#2243

#2246

#2246

#2247

#2248

#2248

#2250

#2251

#2251

#227

#229

#230

#232

#237

#238

#24

#247

#25

#254

#255

#26

#27

#280

#284

#29

#290

#294

#295

#30

#301

#305

#306

#307

#313

#315

#316

#317

#324

#327

#329

#330

#333

#34

#341

#35

#354

#355

#357

#36

#38

#382

#384

#39

#40

#401

#406

#41

#412

#413

#421

#43

#442

#445

#450

#476

#48

#481

#487

#501

#506

#51

#52

#523

#532

#550

#56

#57

#577

#58

#582

#583

#597

#60

#608

#612

#62

#621

#622

#626

#638

#64

#640

#643

#644

#645

#650

#651

#654

#657

#658

#659

#662

#663

#664

#665

#667

#668

#67

#670

#684

#685

#691

#697

#699

#7

#702

#71

#717

#719

#72

#721

#722

#730

#731

#732

#743

#750

#751

#753

#754

#759

#761

#77

#770

#775

#778

#781

#787

#791

#795

#798

#799

#803

#808

#809

#81

#810

#813

#814

#815

#819

#820

#83

#835

#839

#840

#842

#847

#848

#852

#86

#88

#880

#886

#889

#891

#892

#893

#897

#898

#899

#902

#904

#906

#911

#913

#915

#916

#925

#926

#927

#931

#935

#936

#940

#943

#954

#956

#970

#974

#978

#99

#998

paper-ktft-v1

paper-ktft-v1.1

v0.1.0

v0.1.1

v0.1.2

v0.1.3

v0.1.4

v0.2.0

v0.2.1

v0.2.1.post1

v0.2.2

v0.2.2rc1

v0.2.2rc2

v0.2.3

v0.2.3post1

v0.2.3post2

v0.2.4

v0.2.4post1

v0.3

v0.3.1

v0.3.2

v0.4.1

v0.4.2

v0.4.3

v0.4.4

v0.5.0

v0.5.0.post1

v0.5.1

v0.5.2.post1

v0.5.3

v0.6.1

v0.6.1.post1

v0.6.2

v0.6.2.post1

v0.6.2.post2

v0.6.2.post3

v0.6.3

v0.6.3.post1

v0.6.4

v0.7.0

v0.7.0.post1

v0.7.0.post4

v0.7.1

v0.7.2

Mono Color

• 93704cba0a deploy: 2de96a1f05 ovowei 2025-04-09 09:35:35 +00:00
• 2de96a1f05 Merge pull request #1095 from kvcache-ai/update-llama4-tutorial Jianwei Dong 2025-04-09 17:35:14 +08:00
• ecc3028c13 update llama4 tutorial djw 2025-04-09 09:34:04 +00:00
• a74a58d864 Merge pull request #1091 from aubreyli/add_g++ Azure 2025-04-09 14:40:30 +08:00
• 877aec858e Merge branch 'kvcache-ai:main' into main Yuhao Tsui 2025-04-09 11:46:39 +08:00
• 45d20fa87b balance_serve: Add g++ to compiler list Aubrey Li 2025-04-09 11:25:35 +08:00
• 9037bf30d5 Merge pull request #1090 from kvcache-ai/Atream-patch-1 Atream 2025-04-09 10:54:37 +08:00
• 3b9e16cec7 Update attention.py Atream 2025-04-09 10:54:00 +08:00
• 94476ce5cc Merge pull request #1085 from kvcache-ai/qiyuxinlin-patch-5 wang jiahao 2025-04-08 19:19:37 +08:00
• 23ceb1c049 Update balance-serve.md wang jiahao 2025-04-08 19:19:00 +08:00
• 41ce92bb22 Merge pull request #1084 from kvcache-ai/fix-config wang jiahao 2025-04-08 19:14:07 +08:00
• 64de784328 format kvc2, delete quant_configs, move model_configs to ~/.ktransformers qiyuxinlin 2025-04-08 10:06:07 +00:00
• 10fd2e281f Merge pull request #1079 from kvcache-ai/fix-compile Atream 2025-04-08 14:36:31 +08:00
• 9dd24ecd72 fix compile, add abi check to setup.py Atream 2025-04-08 06:18:30 +00:00
• f4ae7c85ed Merge pull request #1069 from kvcache-ai/qiyuxinlin-patch-4 wang jiahao 2025-04-07 19:20:00 +08:00
• 2fcdbee769 Update balance-serve.md wang jiahao 2025-04-07 19:19:49 +08:00
• 77c6cc82ac Merge pull request #1063 from aubreyli/KLinearCPUInfer.forward-fix Azure 2025-04-07 15:10:46 +08:00
• 6463070b16 Merge pull request #1064 from kvcache-ai/fix-temperature wang jiahao 2025-04-07 12:32:28 +08:00
• ec03bcbd7f fix temperature=0, flashinfer sample error dongjw 2025-04-07 12:30:47 +08:00
• aac0c91d02 Merge pull request #1060 from kvcache-ai/fix-compile Atream 2025-04-07 12:10:31 +08:00
• 12a4c631df Fix TypeError when invoke KLinearCPUInfer.forward() Aubrey Li 2025-04-07 12:02:27 +08:00
• fa87c1aeea Update CMakeLists.txt Atream 2025-04-07 10:32:30 +08:00
• ad2009425c Update CMakeLists.txt Atream 2025-04-07 10:32:12 +08:00
• f53d5aa979 Create CMakeLists.txt Atream 2025-04-07 10:30:55 +08:00
• 6ca743ed7a Merge pull request #1049 from kvcache-ai/qiyuxinlin-patch-3 wang jiahao 2025-04-05 11:49:16 +08:00
• 6cbe044aae Update balance-serve.md wang jiahao 2025-04-05 11:49:05 +08:00
• 15a05e4cc0 deploy: 8a1313ca4e qiyuxinlin 2025-04-04 15:45:23 +00:00
• 8a1313ca4e Merge pull request #1044 from 255doesnotexist/patch-1 wang jiahao 2025-04-04 23:45:03 +08:00
• 578d3d9d09 📝 Docs: Clarify CMake version requirement for CUDA dialects 255 2025-04-04 20:11:59 +08:00
• 6617549de0 Merge pull request #1043 from kvcache-ai/KMSorSMS-patch-2 v0.2.4post1 ZiWei Yuan 2025-04-04 16:02:43 +08:00
• a5608dcb80 🔖 release v0.2.4post1 ZiWei Yuan 2025-04-04 16:01:25 +08:00
• af36075bda Merge pull request #1042 from kvcache-ai/v0.2.4-fix wang jiahao 2025-04-04 15:43:48 +08:00
• be84d04253 Fix bug with non-base-multiple chunk_size, update test examples, and resolve issue with writing model_config. Hugging Face URL input is still unsupported. dongjw 2025-04-04 15:41:07 +08:00
• 64e6aa026a Merge pull request #1034 from kvcache-ai/patch_config ZiWei Yuan 2025-04-03 19:57:04 +08:00
• b151a98cab 🔧 update config.yaml setting default config liam 2025-04-03 11:55:50 +00:00
• ca9695b488 Merge pull request #1033 from kvcache-ai/Atream-patch-1 Atream 2025-04-03 17:13:26 +08:00
• e36ddc36a8 Update modeling_deepseek_v3.py Atream 2025-04-03 17:13:06 +08:00
• 016d11e6d4 Merge pull request #1030 from ambitiousCC/main wang jiahao 2025-04-03 16:00:07 +08:00
• 47a89ae752 Merge pull request #1031 from wangkuigang-yewu-cmss/doc-update wang jiahao 2025-04-03 15:58:12 +08:00
• c590583262 doc upgrade: model_path requirements and reasoning wangkuigang-yewu-cmss 2025-04-03 15:16:56 +08:00
• 2c3a3a1e1c slove [Bug] #1023 Qin's repo 2025-04-03 14:37:32 +08:00
• 50eb8e3677 deploy: 72e8e16fa4 qiyuxinlin 2025-04-03 04:45:15 +00:00
• 72e8e16fa4 Merge pull request #1029 from kvcache-ai/mian-update-doc wang jiahao 2025-04-03 12:44:59 +08:00
• 1b7672937b update install doc and fix local_chat bug dongjw 2025-04-03 12:42:41 +08:00
• ab0b0f4ea1 fix local_chat and update balance-serve and SUMMARY doc dongjw 2025-04-03 12:19:43 +08:00
• f6ca3515b5 deploy: 9654bc1c5b KMSorSMS 2025-04-03 04:02:31 +00:00
• 9654bc1c5b Merge pull request #1027 from kvcache-ai/KMSorSMS-patch-1 ZiWei Yuan 2025-04-03 12:02:18 +08:00
• a0ce48ee21 Update SUMMARY.md ZiWei Yuan 2025-04-03 12:00:34 +08:00
• f7a8a91f46 Merge pull request #1024 from kvcache-ai/mian-update-doc wang jiahao 2025-04-03 10:51:54 +08:00
• 8acb270c90 delete sudo install dongjw 2025-04-03 10:46:52 +08:00
• 795524cacc Merge pull request #954 from aubreyli/yaml_marlin_fix Atream 2025-04-02 15:00:37 +08:00
• ec12429c46 Merge pull request #1005 from fishingfly/improve/backend-error-msg Atream 2025-04-02 14:54:23 +08:00
• ac95b6c710 Merge pull request #1015 from kvcache-ai/qiyuxinlin-patch-1 v0.2.4 wang jiahao 2025-04-02 14:22:30 +08:00
• ee179c2ad0 Update balance-serve.md wang jiahao 2025-04-02 14:22:15 +08:00
• a41d216393 Merge pull request #1013 from kvcache-ai/work-concurrent wang jiahao 2025-04-02 14:09:10 +08:00
• 4ed9744ebb update readme dongjw 2025-04-02 14:02:57 +08:00
• b62cefaec9 update readme dongjw 2025-04-02 13:11:01 +08:00
• d41dd23b14 update Dockerfile dongjw 2025-04-02 12:10:58 +08:00
• 65798994cb update Dockerfile dongjw 2025-04-02 12:04:09 +08:00
• 56a18ad02c change tag v0.2.4 dongjw 2025-04-01 21:07:13 +08:00
• d98433c2d1 update git action env, add USE_BALANCE_SERVE=1 Azure-Tang 2025-04-01 12:56:19 +00:00
• 5c7ed7b579 fix top_p = 0 bug dongjw 2025-04-01 20:38:33 +08:00
• aeabd783b0 update git action env, add BALANCE_SERVE=1 Azure-Tang 2025-04-01 11:21:55 +00:00
• 31677181c3 Fix ktransformers-server flashinfer wrapper position arg issue; Fix db position issue Azure-Tang 2025-04-01 07:30:23 +00:00
• 203b853c75 rm KMoEGateDeepSeekV3, fall back to KMoEGate Azure-Tang 2025-04-01 07:13:05 +00:00
• 3a5330b215 Merge branch 'main' into work-concurrent Azure-Tang 2025-04-01 06:48:19 +00:00
• 7549ff335a fix: refine backend error message to include ROCM_HOME fishingfly 2025-04-01 10:50:38 +08:00
• 80c5cbecdd add nlohmann Atream 2025-04-01 10:38:45 +08:00
• 9360d1e3c8 add submodules Atream 2025-03-31 23:20:29 +08:00
• 25cee5810e add balance-serve, support concurrence Atream 2025-03-31 22:55:32 +08:00
• 8d0292aa44 refactor folders Atream 2025-03-31 22:45:37 +08:00
• 84164f584c Update completions.py Yuhao Tsui 2025-03-26 15:39:46 +08:00
• 52fa671c10 Merge branch 'kvcache-ai:main' into main Yuhao Tsui 2025-03-26 11:06:00 +08:00
• f142f4dff3 Merge pull request #956 from kvcache-ai/Atream-patch-7 Atream 2025-03-22 12:14:48 +08:00
• d4c6c2bb02 Update README.md Atream 2025-03-22 12:14:36 +08:00
• a12e8ab46e yaml: fix Marlin AssertionError Aubrey Li 2025-03-21 23:58:20 +08:00
• f4d52d1f0c Restore CPU offloading capability Aubrey Li 2025-03-21 10:04:31 +08:00
• 05f6cede37 Merge pull request #943 from SkqLiao/main Jiaqi Liao 2025-03-20 18:49:34 +08:00
• 6d4626a5d9 fix params SkqLiao 2025-03-20 18:48:51 +08:00
• ddd35d5be9 Merge pull request #940 from kvcache-ai/Atream-patch-6 Atream 2025-03-20 14:54:20 +08:00
• 633af5d235 Update gate.py Atream 2025-03-20 14:54:01 +08:00
• 8cc4df980e use DeepSeek V3 instead of R1 for benchmarking SkqLiao 2025-03-20 11:59:03 +08:00
• 32a91c78c1 Merge pull request #935 from SkqLiao/main Jiaqi Liao 2025-03-20 10:14:37 +08:00
• e7d7d2705c rename CI/CD SkqLiao 2025-03-20 10:11:24 +08:00
• 19c824f9d0 change cpu-infer due to actual cpu cores on self-hosted server. SkqLiao 2025-03-20 10:10:52 +08:00
• 649489dc67 Merge pull request #931 from SkqLiao/main Jiaqi Liao 2025-03-19 21:35:24 +08:00
• bad334fa5b fix path SkqLiao 2025-03-19 21:28:58 +08:00
• bc369b256c add CI/CD for human eval score benchmarking SkqLiao 2025-03-19 21:25:21 +08:00
• 8be56a0190 Merge pull request #927 from kvcache-ai/fix-gate-precision Atream 2025-03-19 16:16:31 +08:00
• b453333f60 Update gate.py Atream 2025-03-19 16:14:54 +08:00
• 6ca233cca3 Merge pull request #926 from kvcache-ai/Atream-patch-5 Atream 2025-03-19 12:17:09 +08:00
• 44599229cd Update gate.py Atream 2025-03-19 12:16:48 +08:00
• aa8f985f85 Merge pull request #925 from kvcache-ai/fix-gate-compile Atream 2025-03-19 11:44:41 +08:00
• 114995355b fix-gate-compile Atream 2025-03-19 11:27:18 +08:00
• 19b153b725 deploy: e788248364 KMSorSMS 2025-03-17 09:55:41 +00:00
• e788248364 Merge pull request #916 from kvcache-ai/patch_v0.2.3post2 ZiWei Yuan 2025-03-17 17:55:30 +08:00
• 4748a912e2 📝 fix typo ktransformer->ktransformers liam 2025-03-17 17:54:00 +08:00
• 8b51b0f058 Merge pull request #915 from kvcache-ai/Atream-patch-4 Atream 2025-03-17 17:05:39 +08:00
• 167506b779 Update DeepSeek-V3-Chat-multi-gpu-marlin.yaml Atream 2025-03-17 17:05:01 +08:00
• c9a0c44213 Update DeepSeek-V3-Chat-multi-gpu-fp8-linear-ggml-experts.yaml Atream 2025-03-17 17:03:52 +08:00