RYDE-WORK/ktransformers
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/ktransformers.git synced 2026-02-07 07:03:27 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Commit Graph

  • ae5d9e11a9
         Merge pull request #227 from hrz6976/main Azure 2025-02-14 10:35:11 +08:00
  • e65be580ab
         Fix dead link problem Guangdong Liu 2025-02-14 09:57:57 +08:00
  • bb35dc5b0d init support for MLA using Attention kernel Atream 2025-02-13 15:01:14 +00:00
  • a456e25a54
         Merge pull request #200 from devin2255/main ZiWei Yuan 2025-02-13 22:22:25 +08:00
  • e490265242
         feat: add GitHub Actions workflow for building Docker image Hand Sonic 2025-02-13 22:09:49 +08:00
  • d04b570fb5 edit README_ZH.md && add DeepseekR1_V3_tutorial_zh.md dhliu 2025-02-13 21:14:44 +08:00
  • aa21edd2fe
         Merge pull request #230 from kvcache-ai/updata-wechatgroup-1 Atream 2025-02-13 19:33:51 +08:00
  • 5fb9d65512
         Add files via upload Atream 2025-02-13 19:33:01 +08:00
  • ade346e09a
         Delete WeChatGrouop.png Atream 2025-02-13 19:31:46 +08:00
  • 127965494c
         Merge pull request #229 from kvcache-ai/updata-wechatgroup Atream 2025-02-13 19:31:13 +08:00
  • 30e8e6a32a
         Add files via upload Atream 2025-02-13 19:30:39 +08:00
  • 2c3dcd9774 Add a lock to server inference() hrz6976 2025-02-13 10:05:22 +00:00
  • 76b081879a
         Merge pull request #224 from kvcache-ai/server_support ZiWei Yuan 2025-02-13 17:28:08 +08:00
  • 8d5ebe49ab 📝 ⚡ fix some debug output and update doc liam 2025-02-13 17:25:12 +08:00
  • ad2c52d72a 📝 update doc liam 2025-02-13 17:16:27 +08:00
  • 8324e7fd9b
         Merge pull request #220 from TensorBlock/main Azure 2025-02-13 16:41:39 +08:00
  • c74453d8ca 📝 add doc support and fix bug in qwen2 liam 2025-02-13 16:26:31 +08:00
  • aea4243712 Add optimization config for Deepseek V3/R1 with 4 GPUs MorphisZhang 2025-02-13 16:32:28 +08:00
  • 318c88cbeb add README_ZH.md dhliu 2025-02-13 12:43:06 +08:00
  • 8bad019ef2
         Merge pull request #180 from lusipad/patch-1 Atream 2025-02-13 10:25:30 +08:00
  • 0905d2e270
         Merge pull request #189 from Kattos/main Atream 2025-02-13 10:24:01 +08:00
  • 9b5fd55a3c
         Merge pull request #190 from kvcache-ai/KMSorSMS-patch-2 ZiWei Yuan 2025-02-13 10:18:08 +08:00
  • 36ab3d7e6c
         Update README.md ZiWei Yuan 2025-02-13 10:17:56 +08:00
  • 01655f7500 fix typo in README.md cuichengyi 2025-02-13 10:12:04 +08:00
  • a0c16db352
         Merge pull request #183 from kvcache-ai/update-WeChatgroup Atream 2025-02-13 09:16:30 +08:00
  • 78cc219274
         Delete WeChatGrouop.jpg Atream 2025-02-13 09:15:57 +08:00
  • ea76f7910a
         Add files via upload Atream 2025-02-13 09:15:30 +08:00
  • 8384badc69
         doc: fix clerical error lusipad 2025-02-13 07:27:27 +08:00
  • 9a3d4c290c
         Merge pull request #170 from feeeei/main Atream 2025-02-12 18:27:11 +08:00
  • e7dd5b250d
         Update release date info feeeei 2025-02-12 17:47:22 +08:00
  • 9e42f33c29
         Merge pull request #166 from kvcache-ai/update-yaml Azure 2025-02-12 17:00:04 +08:00
  • 101db0e9de Merge branch 'main' into update-yaml Azure 2025-02-12 08:56:03 +00:00
  • 3897f001f5 update FAQ Azure 2025-02-12 08:50:58 +00:00
  • 7e58f9d254
         Merge pull request #165 from kvcache-ai/KMSorSMS-patch-1 ZiWei Yuan 2025-02-12 16:44:10 +08:00
  • 193d6300bf
         Update FAQ.md ZiWei Yuan 2025-02-12 16:43:57 +08:00
  • 370b21e536
         Merge pull request #163 from kvcache-ai/update-wechatgroup-1 Atream 2025-02-12 16:33:32 +08:00
  • 9a9fd0167f
         Add files via upload Atream 2025-02-12 16:33:20 +08:00
  • 62011fd63e
         Merge pull request #158 from jinmmd/patch-1 Atream 2025-02-12 15:58:40 +08:00
  • 660730e55c
         Merge pull request #160 from kvcache-ai/updata-wechatgroup Atream 2025-02-12 15:58:08 +08:00
  • 9c717651c5
         Add files via upload Atream 2025-02-12 15:57:55 +08:00
  • 6e0565a275
         Update README.md jinmmd 2025-02-12 14:48:56 +08:00
  • 2ad7fc19f0
         Merge pull request #153 from kvcache-ai/update-wechatgroup Atream 2025-02-12 12:58:23 +08:00
  • 696897dfe3
         update-wechatgroup Atream 2025-02-12 12:57:59 +08:00
  • 4ae2e81c38
         Merge pull request #152 from kvcache-ai/server_support ZiWei Yuan 2025-02-12 12:45:13 +08:00
  • 4385e85096 ⚡ support force thinking liam 2025-02-12 12:43:53 +08:00
  • f30c6482a5
         Merge pull request #151 from kvcache-ai/update-yaml Azure 2025-02-12 12:14:37 +08:00
  • 0564ac8465 update marlin expert example Azure 2025-02-12 04:11:00 +00:00
  • 6f3a39be08 ⚡ update force_think config liam 2025-02-12 12:10:16 +08:00
  • e536e1420d ⚡ update force_think liam 2025-02-12 11:42:55 +08:00
  • a2fc2a8658
         Merge pull request #144 from kvcache-ai/KMSorSMS-patch-1 ZiWei Yuan 2025-02-11 22:07:37 +08:00
  • cfbdb6656a
         Update README.md ZiWei Yuan 2025-02-11 22:07:10 +08:00
  • c47368be3e
         Update README.md ZiWei Yuan 2025-02-11 22:01:34 +08:00
  • e34df7608c
         Merge pull request #143 from kvcache-ai/add-wechat-group-1 Atream 2025-02-11 20:05:07 +08:00
  • 6cfa125eb7
         Update README.md Atream 2025-02-11 20:04:55 +08:00
  • 75c141ebce
         Merge pull request #142 from kvcache-ai/wechat-group Atream 2025-02-11 19:55:27 +08:00
  • 6d2e50ec9a
         Update README.md Atream 2025-02-11 19:55:13 +08:00
  • 94affa6ec9
         Merge pull request #141 from kvcache-ai/add-wechat-group Atream 2025-02-11 19:50:33 +08:00
  • 5c0bbdc3d7
         Add files via upload Atream 2025-02-11 19:49:37 +08:00
  • 2136ad6636
         Merge pull request #135 from kvcache-ai/add_R1_thinking ZiWei Yuan 2025-02-11 15:45:02 +08:00
  • d07087a7e2 ⚡ support R1 force thinking liam 2025-02-11 14:02:19 +08:00
  • a339f573f0
         Merge pull request #127 from squik67/patch-1 UnicornChan 2025-02-11 09:44:55 +08:00
  • dbaecd0ca5
         Merge pull request #128 from kvcache-ai/doc_add ZiWei Yuan 2025-02-10 22:15:40 +08:00
  • c6c83a62ef 📝 update liam 2025-02-10 22:14:36 +08:00
  • 27d16ae0a4
         Update README.md squik67 2025-02-10 15:06:22 +01:00
  • b890a9894a
         Merge pull request #126 from kvcache-ai/update-readme-add-note-of-GGUF-Path Atream 2025-02-10 21:55:34 +08:00
  • a8ac931fe2
         Update README.md Atream 2025-02-10 21:54:30 +08:00
  • cf598db95a
         Merge pull request #124 from kvcache-ai/feat-DeepSeekV3 ZiWei Yuan 2025-02-10 15:07:34 +08:00
  • e45e757fc8 📝 fix doc liam 2025-02-10 14:42:22 +08:00
  • 7527619f53
         Merge pull request #122 from kvcache-ai/feat-DeepSeekV3 UnicornChan 2025-02-10 13:54:46 +08:00
  • f4903d549d
         Merge pull request #123 from RodriMora/add_models_endpoints UnicornChan 2025-02-10 13:54:13 +08:00
  • 6f0fe953e1 ⚡ release v0.2.0 liam 2025-02-10 13:52:24 +08:00
  • 83401dbb3b ⚡ ready to publish liam 2025-02-10 12:29:23 +08:00
  • f892d22849 ⚡ update v3 liam 2025-02-10 11:45:46 +08:00
  • aecb50f0d1 ⚡ fix typo readme liam 2025-02-10 11:36:46 +08:00
  • 0f73f40da0 ⚡ add Summary part liam 2025-02-10 11:31:58 +08:00
  • 323cff15d1 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktrans_v0.2_dev into feat-DeepSeekV3 liam 2025-02-10 11:17:57 +08:00
  • 3d7dfd6151 ⚡ fix typo liam 2025-02-10 11:12:52 +08:00
  • 402b71446b [fix] fix pyproject.toml unicornchan 2025-02-10 03:15:26 +00:00
  • 107e4be417 ⚡ fix typo liam 2025-02-10 10:50:40 +08:00
  • 910d8c842a Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktrans_v0.2_dev into feat-DeepSeekV3 liam 2025-02-10 10:15:45 +08:00
  • cff68532ce ⚡ fix typo liam 2025-02-10 09:52:48 +08:00
  • e968fa8d72 [feature] add flash_attn to requirements unicornchan 2025-02-10 01:52:39 +00:00
  • fd481af193 ⚡ update v0.3 preview liam 2025-02-10 09:48:14 +08:00
  • 6dd4fa0e87 ⚡ improve readme liam 2025-02-10 09:38:26 +08:00
  • fd8037cda1 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktrans_v0.2_dev into feat-DeepSeekV3 unicornchan 2025-02-10 01:01:14 +00:00
  • c7e6d09068 [feature] update version and github action jobs for package unicornchan 2025-02-10 01:00:57 +00:00
  • 2d684ee96a Small fix chenht2022 2025-02-09 16:25:43 +00:00
  • 6b33f41de4 Add V0.3-preview doc chenht2022 2025-02-09 16:08:16 +00:00
  • 098602b08f ⚡ v0.2 ongoing liam 2025-02-09 22:39:01 +08:00
  • bf1d413be0 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktransformers into feat-DeepSeekV3 liam 2025-02-08 13:17:10 +08:00
  • c18ecd7b7f ⚡ add flush print in local_chat output and change default optimize yaml of deepseekv3 to single gpu liam 2025-02-08 13:15:52 +08:00
  • b1bff2a405 Added simple /models endpoint to work with frontends that don't allow bypass check like Openweb-ui RodriMora 2025-02-07 10:30:39 +01:00
  • c4d9bc6670 support KExpertsMarlin backend Azure 2025-02-07 05:57:40 +00:00
  • 0262f954c7 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktransformers into feat-DeepSeekV3 liam 2025-02-06 22:39:48 +08:00
  • 3dca28d23b ⚡ fix moe.cpp int overflow problem liam 2025-02-06 22:39:16 +08:00
  • 027b11266c modify moeinfer param Azure 2025-02-06 14:07:38 +00:00
  • ee24a27001 update v3 single gpu rule yaml; Azure 2025-02-04 16:14:35 +00:00
  • 907251c743 done support deepseekv3 Azure 2025-02-04 15:53:38 +00:00
  • f748cd29f0 fix rope; update moegate Azure 2025-02-01 18:05:45 +00:00
  • f873558a89 update rope calculation; update modeling.py; update gate for moe Azure 2025-02-01 07:32:21 +00:00