Commit Graph

  • f46b3fd51c Merge pull request #778 from Conless/fix-shape Atream 2025-03-03 19:58:52 +08:00
  • 01755a60c0 fix: wrong shape in KLinearMarlin. Yi Pan 2025-03-03 17:34:37 +08:00
  • 4e43e8a4ee Merge pull request #775 from kvcache-ai/Atream-patch-1 Atream 2025-03-03 16:50:02 +08:00
  • 8963ae7817 Update __init__.py Atream 2025-03-03 16:49:50 +08:00
  • 659583a92c Merge pull request #770 from SkqLiao/main Atream 2025-03-03 14:35:26 +08:00
  • 216a63b858 Merge pull request #754 from moonshadow-25/dev023 Azure 2025-03-03 14:19:33 +08:00
  • 7d96e2eeba fix environment name Jiaqi Liao 2025-03-03 14:01:40 +08:00
  • 3d62579a6a fix environment name Jiaqi Liao 2025-03-03 13:55:40 +08:00
  • 5fe0d138ca add install job for self-host testing Jiaqi Liao 2025-03-03 13:52:13 +08:00
  • 48b9800790 Merge pull request #759 from 3wweiweiwu/fix_top_p_typo v0.2.2 wang jiahao 2025-03-02 13:58:11 +08:00
  • bb54b68e5c Merge pull request #761 from kvcache-ai/fix-server-bug wang jiahao 2025-03-02 13:56:46 +08:00
  • 7cdf8139f0 fix ollama api temperature bug 1668068727@qq.com 2025-03-02 13:55:26 +08:00
  • 3aa0cfc29d fix typo for top_p Wix Woo 2025-03-01 20:15:36 +00:00
  • 69382e58f9 Merge pull request #313 from MuWinds/main Atream 2025-03-01 23:24:44 +08:00
  • ca1dc1e7d1 Merge branch 'main' into main Atream 2025-03-01 23:24:10 +08:00
  • 505f4e2c35 Merge pull request #753 from ningpengtao-coder/main Atream 2025-03-01 23:22:13 +08:00
  • d24d369332 iq1s files moonshadow-25 2025-03-01 22:44:06 +08:00
  • c513ae59c3 iq1s files moonshadow-25 2025-03-01 22:38:04 +08:00
  • 71286ec1c0 Update local_chat.py 宁鹏涛 2025-03-01 21:52:48 +08:00
  • 9781d1e6f4 iq1s core moonshadow-25 2025-03-01 21:48:25 +08:00
  • 93c5b75716 rem godrosev 2025-03-01 21:25:18 +08:00
  • e6349eb240 iq1s godrosev 2025-03-01 21:00:11 +08:00
  • c7e05926e0 deploy: 761de49843 Atream 2025-03-01 11:57:13 +00:00
  • 761de49843 Merge pull request #751 from kvcache-ai/Atream-patch-2 Atream 2025-03-01 19:57:00 +08:00
  • 735873a32a Update DeepseekR1_V3_tutorial.md Atream 2025-03-01 19:56:46 +08:00
  • bd33a59ecf Merge pull request #750 from kvcache-ai/feat-chunk-prefill-flashinfer Atream 2025-03-01 19:50:52 +08:00
  • fa03ea48dd Merge branch 'main' into feat-chunk-prefill-flashinfer Atream 2025-03-01 11:35:09 +00:00
  • f35e8d41d8 support chunk prefill, support 139K context for 24G VRAM Atream 2025-03-01 11:28:25 +00:00
  • 9b41720d20 🔖 release 0.2.2rc2 v0.2.2rc2 liam 2025-03-01 13:36:01 +08:00
  • 511958d49c Merge pull request #743 from KMSorSMS/main ZiWei Yuan 2025-03-01 00:17:53 +08:00
  • 80e0536fb0 Merge branch 'main' of https://github.com/KMSorSMS/ktransformers into main liam 2025-03-01 00:12:21 +08:00
  • 8ddc990668 ⚡ fix server cache lens liam 2025-03-01 00:09:57 +08:00
  • 494469d4c5 Merge pull request #722 from ZhangShuaiyi/remove_unused Atream 2025-02-28 15:04:21 +08:00
  • 71f4599dee 📝 rm test_prompt liam 2025-02-28 11:44:49 +08:00
  • 1264f9407b Merge pull request #732 from KMSorSMS/main ZiWei Yuan 2025-02-28 11:28:06 +08:00
  • a0e7afa432 ⚡ fox docker build liam 2025-02-28 11:25:34 +08:00
  • add415124f Merge pull request #731 from Azure-Tang/update-template Azure 2025-02-28 11:19:52 +08:00
  • bc52969918 fix name Azure 2025-02-28 03:17:33 +00:00
  • 0439cb36d4 Merge pull request #730 from Azure-Tang/update-template Azure 2025-02-28 11:10:29 +08:00
  • 31b01f5b99 update ZH/EN template Azure 2025-02-28 03:09:06 +00:00
  • a34a25d5cc Delete unused code Shuaiyi 2025-02-27 13:18:19 +00:00
  • 7a19f3b781 Merge pull request #721 from kvcache-ai/fix_temperature wang jiahao 2025-02-27 21:01:21 +08:00
  • 22df52e94e fix temperature qiyuxinlin 2025-02-27 21:00:44 +08:00
  • 85e2cc7bf4 Merge pull request #719 from kvcache-ai/fix-use-generation-json Atream 2025-02-27 19:49:41 +08:00
  • e645d84794 use generation config from json file in official repo Atream 2025-02-27 11:48:34 +00:00
  • 5e3c6b4f97 Merge pull request #644 from wtdcode/temperature_top_p_from_request wang jiahao 2025-02-27 18:13:13 +08:00
  • b121ca4df8 Fix according to upstream changes lazymio 2025-02-27 18:11:35 +08:00
  • 26f7b4af11 Merge branch 'main' into temperature_top_p_from_request wang jiahao 2025-02-27 18:08:55 +08:00
  • 1f28f75f55 Merge pull request #717 from kvcache-ai/issue-template Azure 2025-02-27 18:02:34 +08:00
  • c61805dd0a Update issue templates Azure 2025-02-27 17:53:27 +08:00
  • 50c691297f Merge pull request #622 from akemimadoka/fix-msvc Atream 2025-02-27 17:42:00 +08:00
  • 0422152cf3 Merge pull request #670 from akemimadoka/fix-win Atream 2025-02-27 17:40:27 +08:00
  • 798e1d0cfa Merge pull request #532 from xv44586/fix-sse-formatting Atream 2025-02-27 12:19:23 +08:00
  • f403cde6d4 Merge pull request #650 from ceerRep/main Atream 2025-02-27 12:16:53 +08:00
  • 1d5d5faef6 Merge pull request #626 from cyhasuka/main Atream 2025-02-27 12:13:10 +08:00
  • 8db6a4d402 Merge branch 'main' into main Atream 2025-02-27 12:12:32 +08:00
  • 3c8c580580 Merge pull request #691 from swu-hyk/ollama_api_chat wang jiahao 2025-02-27 11:17:48 +08:00
  • 74c92ee5c9 deploy: ca93cf7548 Azure-Tang 2025-02-26 15:45:38 +00:00
  • ca93cf7548 Merge pull request #702 from Azure-Tang/update-readme Azure 2025-02-26 23:45:24 +08:00
  • c05ebb74b1 Update fp8 doc; Update install.md broken link Azure 2025-02-26 15:43:08 +00:00
  • df3866caa5 deploy: 3ebe17eb63 Atream 2025-02-26 14:05:02 +00:00
  • 3ebe17eb63 Merge pull request #699 from kvcache-ai/Atream-patch-1 Atream 2025-02-26 22:04:45 +08:00
  • 369f4d917d Update DeepseekR1_V3_tutorial.md Atream 2025-02-26 22:04:29 +08:00
  • 9650893adc Merge pull request #697 from kvcache-ai/fix-yaml Atream 2025-02-26 21:54:01 +08:00
  • 90eb87b3fc Update DeepSeek-V3-Chat-multi-gpu-marlin.yaml Atream 2025-02-26 21:53:50 +08:00
  • ec7e912fee modify swu-hyk 2025-02-26 19:21:30 +08:00
  • 68e7df3a25 implementation of chat routing for Ollama swu-hyk 2025-02-26 17:05:00 +08:00
  • 9660b2cc1e Merge pull request #685 from vproxy-tools/main Chen Hongtao 2025-02-26 15:35:19 +08:00
  • e7ebb26370 Merge pull request #684 from KMSorSMS/main ZiWei Yuan 2025-02-26 15:06:51 +08:00
  • ffb86c66e3 ⚡ fix experts torch liam 2025-02-26 15:04:25 +08:00
  • de082f141c ⚡ fix cd error liam 2025-02-26 14:54:47 +08:00
  • b2bff17775 fix numa cpu distribution wkgcass 2025-02-26 14:48:22 +08:00
  • 8817777e11 Fix RuntimeError on Windows caused by integer overflow in np.prod akemimadoka 2025-02-26 03:50:12 +08:00
  • b9680cf5a4 deploy: 99f6e42113 Azure-Tang 2025-02-25 17:09:50 +00:00
  • 312d29f24e deploy: 31bc990677 Azure-Tang 2025-02-25 16:27:53 +00:00
  • 99f6e42113 Merge pull request #668 from KMSorSMS/main Azure 2025-02-26 00:21:09 +08:00
  • 3ad12751cf 📝 update more detail and fix typo liam 2025-02-26 00:17:02 +08:00
  • 31bc990677 Merge pull request #667 from Azure-Tang/update-readme Azure 2025-02-26 00:01:46 +08:00
  • 05339ad0ef 📝 update benchmark.md liam 2025-02-25 23:56:19 +08:00
  • bb6920ed72 update doc Azure 2025-02-25 15:46:15 +00:00
  • 9c71bcb0bb Merge pull request #665 from KMSorSMS/v0.2.2rc1 v0.2.2rc1 ZiWei Yuan 2025-02-25 22:07:19 +08:00
  • ddf3339339 ⚡ release v0.2.2rc1 liam 2025-02-25 22:06:36 +08:00
  • ac8307a849 deploy: 8333a4d874 Azure-Tang 2025-02-25 13:47:57 +00:00
  • 8333a4d874 Merge pull request #663 from kvcache-ai/develop-0.2.2 Azure 2025-02-25 21:47:36 +08:00
  • c6e4e1c3c5 Merge pull request #662 from Azure-Tang/support-fp8 Azure 2025-02-25 21:45:19 +08:00
  • 91c1619296 Merge branch 'develop-0.2.2' into support-fp8 Update README.md Azure 2025-02-25 13:36:21 +00:00
  • 13974eb264 Update DeepseekR1_V3_tutorial.md Atream 2025-02-25 21:36:52 +08:00
  • 03f8bc9f79 Update DeepseekR1_V3_tutorial.md add long context Atream 2025-02-25 21:35:31 +08:00
  • 2c0cce90d0 add fp8 multi gpu yaml example Azure 2025-02-25 13:32:09 +00:00
  • d9b2895bd3 Merge branch 'fix-update-flashinfer_wrapper_local_chat' into develop-0.2.2 Atream 2025-02-25 12:47:48 +00:00
  • 477ac28a9c fix-update-flashinfer_wrapper_local_chat Atream 2025-02-25 12:47:31 +00:00
  • 7e5962af3d fix fp8 multi gpu; update FQA Azure 2025-02-25 10:52:29 +00:00
  • 89b55052b8 Merge pull request #659 from KMSorSMS/develop-0.2.2 ZiWei Yuan 2025-02-25 17:47:05 +08:00
  • 1b5ac67fca 📝 add benchmark.md liam 2025-02-25 17:45:17 +08:00
  • 1aa10e93b3 Merge pull request #658 from KMSorSMS/develop-0.2.2 ZiWei Yuan 2025-02-25 17:22:34 +08:00
  • 0ca0b99fab ⚡ update git ignore add docker dev container liam 2025-02-25 17:19:19 +08:00
  • 5474be5299 Merge branch 'main' into develop-0.2.2 Azure 2025-02-25 09:04:22 +00:00
  • 021822dd01 update FAQ Azure 2025-02-25 09:02:32 +00:00
  • b443c7dfa2 Merge pull request #657 from kvcache-ai/feat-absorb-for-long-prefill Atream 2025-02-25 16:53:21 +08:00
  • f4c198bd42 support absorb for prefill long context Atream 2025-02-25 08:52:02 +00:00