Commit graph

247 commits

Author SHA1 Message Date
Atream
6cfa125eb7
Update README.md 2025-02-11 20:04:55 +08:00
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
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