Commit Graph
146 Commits
Author SHA1 Message Date
Atream 75c141ebce Merge pull request #142 from kvcache-ai/wechat-group
Update README.md
2025-02-11 19:55:27 +08:00
Atream 6d2e50ec9a Update README.md 2025-02-11 19:55:13 +08:00
Atream 94affa6ec9 Merge pull request #141 from kvcache-ai/add-wechat-group
Add files via upload
2025-02-11 19:50:33 +08:00
Atream 5c0bbdc3d7 Add files via upload 2025-02-11 19:49:37 +08:00
ZiWei Yuan 2136ad6636 Merge pull request #135 from kvcache-ai/add_R1_thinking
⚡ support R1 force thinking
2025-02-11 15:45:02 +08:00
liam d07087a7e2 ⚡ support R1 force thinking 2025-02-11 15:43:41 +08:00
UnicornChan a339f573f0 Merge pull request #127 from squik67/patch-1
Update README.md
2025-02-11 09:44:55 +08:00
ZiWei Yuan dbaecd0ca5 Merge pull request #128 from kvcache-ai/doc_add
📝 update
2025-02-10 22:15:40 +08:00
liam c6c83a62ef 📝 update 2025-02-10 22:14:36 +08:00
squik67 27d16ae0a4 Update README.md
add cpufeature numpy to pip cli
2025-02-10 15:06:22 +01:00
Atream b890a9894a Merge pull request #126 from kvcache-ai/update-readme-add-note-of-GGUF-Path
Update README.md
2025-02-10 21:55:34 +08:00
Atream a8ac931fe2 Update README.md 2025-02-10 21:54:30 +08:00
ZiWei Yuan cf598db95a Merge pull request #124 from kvcache-ai/feat-DeepSeekV3
📝 fix doc
2025-02-10 15:07:34 +08:00
liam e45e757fc8 📝 fix doc 2025-02-10 15:04:04 +08:00
UnicornChan 7527619f53 Merge pull request #122 from kvcache-ai/feat-DeepSeekV3
[Feat] add support to DeepSeekV3
v0.2.0
2025-02-10 13:54:46 +08:00
UnicornChan f4903d549d Merge pull request #123 from RodriMora/add_models_endpoints
Added simple /models endpoint
2025-02-10 13:54:13 +08:00
liam 6f0fe953e1 ⚡ release v0.2.0 2025-02-10 13:52:40 +08:00
liam 83401dbb3b ⚡ ready to publish 2025-02-10 12:29:23 +08:00
liam f892d22849 ⚡ update v3 2025-02-10 11:46:27 +08:00
liam aecb50f0d1 ⚡ fix typo readme 2025-02-10 11:36:46 +08:00
liam 0f73f40da0 ⚡ add Summary part 2025-02-10 11:32:44 +08:00
liam 323cff15d1 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktrans_v0.2_dev into feat-DeepSeekV3 2025-02-10 11:17:57 +08:00
liam 3d7dfd6151 ⚡ fix typo 2025-02-10 11:17:32 +08:00
unicornchan 402b71446b [fix] fix pyproject.toml 2025-02-10 03:15:26 +00:00
liam 107e4be417 ⚡ fix typo 2025-02-10 10:50:40 +08:00
liam 910d8c842a Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktrans_v0.2_dev into feat-DeepSeekV3 2025-02-10 10:15:45 +08:00
liam cff68532ce ⚡ fix typo 2025-02-10 09:52:48 +08:00
unicornchan e968fa8d72 [feature] add flash_attn to requirements 2025-02-10 01:52:39 +00:00
liam fd481af193 ⚡ update v0.3 preview 2025-02-10 09:49:56 +08:00
liam 6dd4fa0e87 ⚡ improve readme 2025-02-10 09:38:26 +08:00
unicornchan fd8037cda1 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktrans_v0.2_dev into feat-DeepSeekV3 2025-02-10 01:01:14 +00:00
unicornchan c7e6d09068 [feature] update version and github action jobs for package 2025-02-10 01:00:57 +00:00
chenht2022 2d684ee96a Small fix 2025-02-09 16:25:43 +00:00
chenht2022 6b33f41de4 Add V0.3-preview doc 2025-02-09 16:08:16 +00:00
liam 098602b08f ⚡ v0.2 ongoing 2025-02-09 22:41:14 +08:00
liam bf1d413be0 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktransformers into feat-DeepSeekV3 2025-02-08 13:17:10 +08:00
liam c18ecd7b7f ⚡ add flush print in local_chat output and change default optimize yaml of deepseekv3 to single gpu 2025-02-08 13:15:52 +08:00
RodriMora b1bff2a405 Added simple /models endpoint to work with frontends that don't allow bypass check like Openweb-ui 2025-02-07 10:30:39 +01:00
Azure c4d9bc6670 support KExpertsMarlin backend 2025-02-07 05:57:40 +00:00
liam 0262f954c7 Merge branch 'feat-DeepSeekV3' of github.com:kvcache-ai/ktransformers into feat-DeepSeekV3 2025-02-06 22:41:25 +08:00
liam 3dca28d23b ⚡ fix moe.cpp int overflow problem 2025-02-06 22:39:16 +08:00
Azure 027b11266c modify moeinfer param 2025-02-06 14:07:38 +00:00
Azure ee24a27001 update v3 single gpu rule yaml; 2025-02-04 16:14:35 +00:00
Azure 907251c743 done support deepseekv3 2025-02-04 15:53:38 +00:00
Azure f748cd29f0 fix rope; update moegate 2025-02-01 18:05:45 +00:00
Azure f873558a89 update rope calculation; update modeling.py; update gate for moe 2025-02-01 07:32:21 +00:00
Azure 5a50b34627 fix hard coding caused by rope dim calculation, load from config now 2025-01-31 15:25:50 +00:00
Azure 476b1d8dc6 support deepseekv3; runable but have precition problem 2025-01-31 08:27:24 +00:00
UnicornChan de7e892f72 Merge pull request #115 from KMSorSMS/main
⚡ rm opt config path default value and fix some config logic bug
2024-11-14 20:07:12 +08:00
liam 04cebec4bb ⚡ rm opt config path default value and fix some config logic bug 2024-11-14 20:02:30 +08:00