Commit Graph

  • 322eaee88e
    Merge b9a5491bbcedbf477e5ffa5198bd92815977e48f into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Ayanahmedkhans 2025-11-25 11:40:28 +00:00
  • b9a5491bbc
    Create Thunder Ayanahmedkhans 2025-11-25 16:39:10 +05:00
  • 97beb70fb2
    Merge e44e45bfc547895415af0ffe43ce429b698497e8 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b EduRills 2025-11-20 20:11:06 -06:00
  • e44e45bfc5
    Add Nairobi Information Collector application Claude 2025-11-21 02:06:23 +00:00
  • 6235d92c50
    Merge de04ffa468ac221c59793f8b5ab79f823341f2d5 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b fmendezespinoza887-max 2025-11-14 17:05:05 +00:00
  • de04ffa468
    Create Github.css fmendezespinoza887-max 2025-11-14 11:04:25 -06:00
  • b99f4bf504
    Merge 6d7aeee7debbbab18d909e44e6ddcf52c7bd7f84 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Luca Lowndes 2025-10-29 19:10:45 +11:00
  • 6d7aeee7de
    Update: Revise SGLang Multi-Token Prediction details link Luca Lowndes 2025-10-29 19:10:17 +11:00
  • 6eccb0d712
    Merge 73fe98d4b184bd417114c28da858bbc445646fed into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Libres-coder 2025-10-26 16:53:44 +00:00
  • 73fe98d4b1 feat: implement UE8M0 scale format support for FP8 inference Libres-coder 2025-10-27 00:45:02 +08:00
  • 03962231ec
    Merge 8b5f93df89eb527945375debd351c5da435613e7 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Abhinav 2025-10-25 16:07:09 +00:00
  • 8b5f93df89 Add Flask-based text-only endpoints, requirements, tests and docs for issue #1014 Abhinav 2025-10-25 21:34:53 +05:30
  • 8414f73f3c
    Add GitHub Actions workflow for Python application Abhinav 2025-10-25 21:09:30 +05:30
  • 70ddd25f08
    Merge 21a919d79f47829c1c9b11d7e067af4499fdf063 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Ceaser1717 2025-10-21 10:35:41 +00:00
  • 21a919d79f
    Fix: prevent infinite “A5A5A5...” repetition loop during text generation (Issue #1008) Ceaser1717 2025-10-21 16:02:03 +05:30
  • 031930fb29
    Fix infinite generation loop Ceaser1717 2025-10-19 22:29:20 +05:30
  • 62ce03fae5
    Merge 4c786a9055a48ca2ed7f205eea7dc9561d44a9c8 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b 🇨🇳钟智强 『江西青垣科技』 2025-10-12 07:40:31 +00:00
  • 4c786a9055 (feat) added a simple workflows to prevent github issue spam #1004 🇨🇳钟智强 『江西青垣科技』 2025-10-12 15:38:02 +08:00
  • f1db6e76e0 (feat) added a simple workflows to prevent github issue spam #1004 🇨🇳钟智强 『江西青垣科技』 2025-10-12 15:37:38 +08:00
  • c680f674f2 (feat) added a simple workflows to prevent github issue spam #1004 🇨🇳钟智强 『江西青垣科技』 2025-10-12 15:35:39 +08:00
  • bdda326a96
    Merge bb2b16dca43e5f618dc6733af71120811d38c4ab into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b cyberredin 2025-10-12 07:19:40 +00:00
  • bb2b16dca4
    Create tianmengsquare cyberredin 2025-10-12 03:17:57 -04:00
  • c6f3fa65e7
    Merge 3e30d5b249e62242c247c2ae26b1cf77f95ec498 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Tri Dao 2025-10-09 23:06:37 +00:00
  • 3e30d5b249
    Merge branch 'deepseek-ai:main' into trid/f32-gate-bias Tri Dao 2025-10-09 19:06:34 -04:00
  • ab76fa01ca
    Merge 6847b3d86692438b63a831f7649705c18d7d333b into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Richard Ogundele 2025-09-26 22:19:39 +01:00
  • 6847b3d866
    Merge branch 'deepseek-ai:main' into main Richard Ogundele 2025-09-26 22:18:08 +01:00
  • e36e727e21 add tests for fp8_cast_bf16.py Richard Ogundele 2025-09-26 21:02:46 +01:00
  • 2b692199bc
    Merge 328e6aaaa6ed1266ea36f0c53fe7ae228c868a69 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Bruce-x-1997 2025-09-26 02:44:04 +00:00
  • 328e6aaaa6 add config_kimi_k2.json bruce.xu 2025-09-26 02:40:23 +00:00
  • 8afa456081
    Merge 3b8af8fdfa27985be1a1e8a8eacf69ac7e0c95a6 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b rao118417-hue 2025-09-15 20:19:35 +03:30
  • 3b8af8fdfa
    Create Open World Car + Ghost Mode Game -Complete Game Design Document rao118417-hue 2025-09-15 20:10:17 +03:30
  • 097c3aa290
    Merge 6dc0aa6eedc0624efe4319a4fbcc42084e3bbf81 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b AHMED KENAWY 2025-09-09 11:18:59 +00:00
  • 6dc0aa6eed
    Create index.html AHMED KENAWY 2025-09-09 15:14:57 +04:00
  • f848d71df6
    Merge 7bc8640c9a00b40ef61c8fabf80d6986c008622f into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Cyb3rHunter1337 2025-09-01 14:01:30 +00:00
  • 961cd8ca0a
    Merge aa0726d4b9e8155baf333507109fcff587e7e810 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b xxxyalaxx90xxx 2025-09-01 14:01:28 +00:00
  • 679c14078a
    Merge 91987eddb9dd911b18b4325ea52380ab755a170a into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Bo Li 2025-09-01 14:01:28 +00:00
  • ce106de90b
    Merge 88d7ebbd1e29f20cff11266e4e3c30f402c41630 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Prakash Mohit 2025-09-01 14:01:28 +00:00
  • 982c69ea41
    Merge abaadd9b3e746fc91fcd19dbb79ff4ed615580e3 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Saro 2025-09-01 14:01:26 +00:00
  • 6113a50d00
    Merge 5399f5524fd4d85b00ce38640115fc6b83b9e15a into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Hongvan3799 2025-09-01 14:01:26 +00:00
  • d42b8b1381
    Merge 20c8b4f6b17daad6623efffb3551f972bde3ced1 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Kent Slaney 2025-09-01 14:01:26 +00:00
  • 6bc0d0eb02
    Merge 3421621d7b31fe632bdf1f1771f2ccbac705027c into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b A-transformer 2025-09-01 14:01:24 +00:00
  • 3facb6e7c8
    Merge 84e7789ef8c79af12c3d2414a1610252c0469082 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Yanyue Xie 2025-09-01 14:01:22 +00:00
  • 91a8557c9b
    Merge 57582c60f4243cdbdd83ffcd5a7d42056e242a89 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Xu Song 2025-09-01 14:01:21 +00:00
  • 218f637b05
    Merge d257cbe7331647f7e8e23e8743ca6ff974defcb4 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Abdur Rahman 2025-09-01 14:01:21 +00:00
  • b392f0f010
    Merge d700e0056d819d0f67b1e739282bffa0ccfc68da into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Rakibul Islam 2025-09-01 14:01:17 +00:00
  • 7b643d17ca
    Merge 897291478c05d2fbe69705bd377577dfbec4b4ca into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Tanmay Das 2025-09-01 14:01:17 +00:00
  • 9de97a40f1
    Merge 4e570a99a705502948c29519bebff9fb43ea079b into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Juan Valencia 2025-09-01 14:01:17 +00:00
  • ed11ac644a
    Merge f10ff9c26237af8a96a7b3eff70d37d43609f7f4 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Jason 2025-09-01 14:01:14 +00:00
  • f4f9070a6e
    Merge b156e5450bc29d78fa3365238170de4a7196506b into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Dhieu 2025-09-01 14:01:08 +00:00
  • 652cc9f966
    Merge a7151e67fbc2d61c82c663d1e3e5bd0943977cf6 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b minimalProviderAgentMarket 2025-09-01 14:01:04 +00:00
  • e867d890db
    Merge a5336884cfa952634f355549643dcb781eaec872 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Nripesh Niketan 2025-09-01 00:53:48 +01:00
  • 0111ed3ab1
    Merge d3de9e8d1fcb8efd620bd94661e7ccb635b8283a into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Ritik 2025-08-29 23:53:16 +03:00
  • 79571aa67c
    Merge 37f0b41ac6501266a661ebda3b1eff7bea9f3a1b into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Arupm 2025-08-29 20:56:48 +03:00
  • 423dd5eada
    Merge 8a65a6ae3825e4481f885ee2c2991d0478d9d1fd into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b p1r4t4 2025-08-29 11:40:10 +03:00
  • 766aa14e40
    Merge 1ea5a1a7ed7429e25ba2fa2c76fe74fa5968d348 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Kunal Janjirala 2025-08-29 08:27:17 +03:00
  • a1f2144591
    Merge 9ce2a7b11517e80af9202a962bc663e9a2329e63 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Favaro german 2025-08-28 16:20:12 +08:00
  • 9d18270008
    Merge 630769360a6ebcf79d270e0944f3aa2dfe888693 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b Ye Zhiling 2025-08-28 14:35:31 +08:00
  • c5aa6af85b
    Merge 27067329f95318c2e176cec8b69500da85374fb6 into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b neolithic5452 2025-08-28 14:35:05 +08:00
  • 3e40154dae
    Merge 0499023612a6fdbdfeea8533556ac59d7440dfcd into 9b4e9788e4a3a731f7567338ed15d3ec549ce03b The Prime Mathematician 2025-08-28 08:59:02 +03:30
  • 9b4e9788e4 Merge pull request #969 from youkaichao/rmsnorm main GeeeekExplorer 2025-08-27 17:14:24 +08:00
  • adecc0efbe fix rmsnorm and act_quant_kernel youkaichao 2025-08-27 17:12:13 +08:00
  • 82f6008c8c
    fix act_quant_kernel (#968) youkaichao 2025-08-27 16:23:30 +08:00
  • 4667d669c7 fix act_quant_kernel youkaichao 2025-08-27 16:20:55 +08:00
  • b15f0dbbbe
    support scale_fmt=ue8m0 (#964) youkaichao 2025-08-27 15:30:21 +08:00
  • 080ca93e84 rename config youkaichao 2025-08-27 15:16:41 +08:00
  • 1c6947e6ab
    Merge 1e40f4a73c71ba2e9a5fc3dd58dafcf594c87449 into 4592be48c07f036b32ef971474068aebc489e3e7 Furkan KARAKUZ 2025-08-26 11:55:31 -04:00
  • 7e3b09408e
    Merge 79d72ecd8d4fc09212d216661eb3ac4e6ea72a98 into 4592be48c07f036b32ef971474068aebc489e3e7 Ayush Tiwari 2025-08-26 21:59:50 +07:00
  • 484b42ca4e add clamp min of 1e-4 youkaichao 2025-08-26 18:14:52 +08:00
  • 21b2dfe172 keep improving youkaichao 2025-08-26 18:09:40 +08:00
  • 348e741a11 keep improving youkaichao 2025-08-26 18:08:50 +08:00
  • 0c08ef325b
    Merge 434a9e0ec7e6ed15f7a0017350d6aa0753f8a05f into 4592be48c07f036b32ef971474068aebc489e3e7 Rahul Chaube 2025-08-26 15:38:03 +05:30
  • 3745dc5ab6 support scale_fmt=ue8m0 youkaichao 2025-08-26 17:48:06 +08:00
  • 4592be48c0
    fp32 gate bias Xingkai Yu 2025-08-26 17:39:07 +08:00
  • d6d7cc9860 Add dtype=torch.float32 Tri Dao 2025-08-25 11:47:09 -07:00
  • 27067329f9
    Fix broken TensorRT-LLM link to deepseekv3 neolithic5452 2025-08-21 18:10:39 -07:00
  • 2af264d674
    Update README.md inesggg 2025-08-06 15:49:08 +08:00
  • 0499023612
    Fully optimized text The Prime Mathematician 2025-08-02 10:33:39 +10:00
  • 9870688573
    Update README.md The Prime Mathematician 2025-08-01 14:24:49 +10:00
  • b2253d1807
    Update model.py Janson Lau 2025-07-27 23:42:47 +08:00
  • c21638c56c
    Update model.py Janson Lau 2025-07-27 23:36:35 +08:00
  • 292b8a34d8
    Create model.py Janson Lau 2025-07-27 23:34:37 +08:00
  • b265f3795c
    Delete inference/model.py Janson Lau 2025-07-27 21:54:05 +08:00
  • 9fabdf8ae6
    Create model.py @greptile Janson Lau 2025-07-27 21:32:16 +08:00
  • e1daf07be1
    Delete inference/model.py Janson Lau 2025-07-27 21:31:51 +08:00
  • 55f36bafc7
    Create model.py Janson Lau 2025-07-27 21:30:22 +08:00
  • e5f8de034b
    Delete inference/model.py Janson Lau 2025-07-27 21:30:04 +08:00
  • 94590b9924
    Merge 7813704f781d6489270053bde588c4ac80a2e051 into f6e34dd26772dd4a216be94a8899276c5dca9e43 Yiakwy 2025-07-01 12:04:58 +00:00
  • 7813704f78 add readme yiakwy-xpu-ml-framework-team 2025-07-01 20:04:39 +08:00
  • 31bdaf1112 update script and verified correctness yiakwy-xpu-ml-framework-team 2025-07-01 17:40:04 +08:00
  • 44c403f0d8 add support block-wise quant from bf16 yiakwy-xpu-ml-framework-team 2025-07-01 07:59:03 +08:00
  • 7bc8640c9a
    Update README.md Cyb3rHunter1337 2025-06-21 20:31:55 +06:00
  • 539e9d1789
    Merge 36bc4fc713b856c924bcbb475f4efb5d06a56488 into f6e34dd26772dd4a216be94a8899276c5dca9e43 Pushkar Kumar Saini 2025-06-19 11:24:57 -04:00
  • 58c59ad010
    Merge 7fbf99b32bca7e8774c17b3515af7c860e91905c into f6e34dd26772dd4a216be94a8899276c5dca9e43 Michael Yao 2025-06-18 19:59:09 +08:00
  • 50bf01cba8
    Merge a8b6b9184d0f988cd8b1020aa061bef4b16c8525 into f6e34dd26772dd4a216be94a8899276c5dca9e43 Pushkar Kumar Saini 2025-06-17 20:47:27 +02:00
  • 9614d2d5d9
    Merge 73b8bea98119102c98c4438ed3222bc42d864985 into f6e34dd26772dd4a216be94a8899276c5dca9e43 Nodoubtz 2025-06-16 06:33:03 -04:00
  • aefd2482df
    Merge 54b708d75f08f72c6980a59080cd51f2684568eb into f6e34dd26772dd4a216be94a8899276c5dca9e43 Nodoubtz 2025-06-16 06:33:03 -04:00
  • f6e34dd267
    Merge pull request #903 from yixing1992/main v1.0.0 Liyue Zhang 2025-06-16 14:50:08 +08:00
  • e975062c42
    Update README.md for Huawei Ascend NPU support modes yixing1992 2025-06-16 14:34:28 +08:00
  • a8b6b9184d
    Update kernel.py Pushkar Kumar Saini 2025-06-12 10:40:02 +05:30
  • 36bc4fc713
    Create requirements.txt Pushkar Kumar Saini 2025-06-12 10:32:58 +05:30