Commit Graph

239 Commits

Author SHA1 Message Date
晓雷 44947fe7fa ray launcher before test 2025-07-15 14:22:45 +08:00
bowei.fw 29172e0e10 . 2025-07-14 10:09:24 +08:00
bowei.fw ae20d51cce . 2025-07-13 22:12:54 +08:00
bowei.fw 932f9b9232 32k run 2025-07-13 21:48:48 +08:00
bowei.fw eda0e79725 debug 2025-07-13 15:27:49 +08:00
bowei.fw 34b6941a2f ready for boba 2025-07-12 19:20:02 +08:00
bowei.fw 43b3c3f8d0 slurm run 2025-07-12 17:57:58 +08:00
bowei.fw 0d03141cbc merge slurm launcher 2025-07-12 14:54:49 +08:00
bowei.fw d65df45780 fix 2025-07-12 14:53:43 +08:00
bowei.fw fda19261cd async works 2025-07-12 13:43:57 +08:00
meizhiyu.mzy 1af70c332c . 2025-07-12 12:27:06 +08:00
晓雷 e222cea659 . 2025-07-12 11:43:29 +08:00
meizhiyu.mzy 805437463f sglang server wrapper 2025-07-12 11:08:21 +08:00
bowei.fw bb67116f51 fix 2025-07-12 09:59:09 +08:00
bowei.fw d37405081b fix 2025-07-12 09:45:42 +08:00
bowei.fw 888751da38 qwen2 grpo works 2025-07-12 09:44:50 +08:00
meizhiyu.mzy 4a26f28adf . 2025-07-11 22:56:59 +08:00
晓雷 97511e43ff fix arg parse 2025-07-11 16:47:29 +08:00
晓雷 57ce1213ae merge ppo 2025-07-11 16:24:07 +08:00
晓雷 6acd1696f6 slurm launcher not tested 2025-07-11 16:14:59 +08:00
bowei.fw 0cbddb8aba . 2025-07-11 11:10:55 +08:00
博惟 c38cffc023 PullRequest: 340 [lite] Refactor trainer API into utilities and remove mb_spec in engine methods
Merge branch fw/lite-dev of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/340

Reviewed-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* support fsdp engine and sglang remote engine
* minor fix
* .
* refactor trainer
* add close
* rm mb_spec
* fix
2025-07-10 11:10:10 +08:00
bowei.fw 1bb23f2399 Merge branch 'fw/lite-dev' of code.alipay.com:inclusionAI/AReaL into fw/ppo 2025-07-10 11:08:47 +08:00
bowei.fw 520e38b1ee fix 2025-07-10 11:06:57 +08:00
bowei.fw 347bcc07a6 . 2025-07-10 11:05:08 +08:00
bowei.fw a78fd2dd24 rm mb_spec 2025-07-09 22:16:31 +08:00
bowei.fw 32077b02ed add close 2025-07-09 21:56:27 +08:00
bowei.fw b75aaaf130 refactor trainer 2025-07-09 21:48:28 +08:00
bowei.fw 9d756686cb Merge branch 'lite' of code.alipay.com:inclusionAI/AReaL into fw/lite-dev 2025-07-09 16:57:36 +08:00
博惟 7be4ab0d18 PullRequest: 339 [Fix] Fix some minor issues to pass all tests.
Merge branch fw/lite of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/339

Reviewed-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* support fsdp engine and sglang remote engine
* minor fix
* .
2025-07-09 16:51:26 +08:00
bowei.fw fe1f622841 . 2025-07-09 16:48:57 +08:00
bowei.fw 124184a7b7 minor fix 2025-07-09 16:48:11 +08:00
bowei.fw a6bcab22ba support fsdp engine and sglang remote engine 2025-07-09 16:45:29 +08:00
博惟 15dfbe837c PullRequest: 332 [lite] Support FSDP engines
Merge branch mzy/lite/engines of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/332

Reviewed-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* fsdp2 engine
* fix utils
* add fsdp engine test
* .
* fsdp engine test passed
* unsqueeze immediately before model inputs and after model outputts
* add optimizer save/load, add position id calculation for input
* .
* format
* not to squeeze
* add train and eval api
* .
* .
* improve fsdp engine data preprocessing
* format
* PullRequest: 337 [lite] Add SFT trainer example.
* trainer log
* minor changes
* add update weights from disk
* fix type annotation
2025-07-09 16:24:25 +08:00
郭唯 7a438c0650 PullRequest: 336 add wrapper
Merge branch lite-util-wrapper of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/336

Reviewed-by: 博惟 <bowei.fw@antgroup.com>


* add wrapper
2025-07-09 15:44:27 +08:00
博惟 8771778995 PullRequest: 331 [lite] Support remote sglang engine with corresponding testcases.
Merge branch fw/lite of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/331

Reviewed-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
* add test for sglang remote engine
* fix
2025-07-09 14:18:55 +08:00
博惟 57b9b945ab add readme 2025-07-07 17:46:46 +08:00
garrett4wade cf0db6a43c format 2025-07-07 17:02:32 +08:00
garrett4wade 7ab6755379 Merge branch 'lite' of https://github.com/inclusionAI/AReaL into lite 2025-07-07 17:02:21 +08:00
博惟 e251abbbe8 add remote sglang engine 2025-07-07 17:01:35 +08:00
博惟 3b2f43a295 checkout prev impl 2025-07-07 15:53:34 +08:00
博惟 95c315e0b8 checkout previous implementations 2025-07-07 15:52:44 +08:00
博惟 3a0f1e558c checkout previous impl 2025-07-07 15:51:32 +08:00
博惟 6710d5f275 Merge branch 'lite' of https://code.alipay.com/inclusionAI/AReaL into lite 2025-07-07 15:35:02 +08:00
garrett4wade b6e19dbf60 format 2025-07-07 14:02:59 +08:00
博惟 28c9479981 add tests template 2025-07-07 13:51:23 +08:00
博惟 1006be8a01 add directory structure 2025-07-07 13:49:54 +08:00
博惟 1dfe91c470 add api 2025-07-07 13:47:41 +08:00
Wei Fu 5b7c83b5d9
update qrcode (#153) 2025-07-07 12:28:21 +08:00
Wei Fu 0ff8c59435
[Fix] Merge error fixes. (#152)
* PullRequest: 293 fix get_param_realloc_path

Merge branch xss/debug of git@code.alipay.com:inclusionAI/AReaL.git into gh
https://code.alipay.com/inclusionAI/AReaL/pull_requests/293

Reviewed-by: 博惟 <bowei.fw@antgroup.com>


* fix get_param_realloc_path

* PullRequest: 297 bugfix: reward is always -5

Merge branch xss/debug of git@code.alipay.com:inclusionAI/AReaL.git into gh
https://code.alipay.com/inclusionAI/AReaL/pull_requests/297

Reviewed-by: 博惟 <bowei.fw@antgroup.com>


* bugfix: reward is always -5

* PullRequest: 321 fix checkpoint save dir

Merge branch xss/debug of git@code.alipay.com:inclusionAI/AReaL.git into gh
https://code.alipay.com/inclusionAI/AReaL/pull_requests/321

Reviewed-by: 博惟 <bowei.fw@antgroup.com>


* fix checkpoint save dir

* PullRequest: 328 [Doc] update installation

Merge branch sxj/doc of git@code.alipay.com:inclusionAI/AReaL.git into gh
https://code.alipay.com/inclusionAI/AReaL/pull_requests/328

Reviewed-by: 博惟 <bowei.fw@antgroup.com>


* [Doc] update installation

---------

Co-authored-by: 温差 <xushusheng.xss@antgroup.com>
Co-authored-by: 冰临 <shenxujie.sxj@antgroup.com>
2025-07-07 10:30:27 +08:00