louis_lifu
/
AReaL
mirror of https://github.com/inclusionAI/AReaL
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
882 Commits 12 Branches 4 Tags 21 MiB
Commit Graph

410 Commits

Author SHA1 Message Date
lichangye.lcy 78d0367ff2 0731_2 2025-07-31 16:35:13 +08:00
antoinegg1 c5cd21d5db 0731_2 2025-07-31 15:57:07 +08:00
朱晗 d6a6240655 0731_1 2025-07-31 14:37:55 +08:00
朱晗 4ff813ae9f 0725_format 2025-07-25 19:17:26 +08:00
lichangye.lcy fb1796d941 0725_11 2025-07-25 18:52:29 +08:00
朱晗 60ac19ad04 0725_10padded_image 2025-07-25 15:52:33 +08:00
朱晗 cc3c6bbe5d 0725_9padded_image 2025-07-25 15:50:37 +08:00
朱晗 4f8b17feb9 0725_4padded_image 2025-07-25 15:48:54 +08:00
朱晗 8eaced4036 0725_7 2025-07-25 14:10:28 +08:00
lichangye.lcy 4198cd695c 0725_1 2025-07-25 13:42:42 +08:00
朱晗 b8549ac48a 0724_merge8 2025-07-24 19:54:15 +08:00
朱晗 84be9c9baf Merge remote-tracking branch 'backup/lite' into lcy/refactor 2025-07-24 19:34:26 +08:00
朱晗 f5924b1851 0724_merge7 2025-07-24 19:34:22 +08:00
Wei Fu f299740b1c
[lite] [doc] Add AReaLite design doc as README (#198) 
* PullRequest: 353 [Lite] Add gradient checkpointing to FSDPEngine

Merge branch mzy/add-gradient-ckpt of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/353

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


* add gradient checkpointing

* PullRequest: 354 [lite] GRPO pre-commit: minor changes in FSDP  engine

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/354

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


* .
* .
* .
* .

* PullRequest: 355 [Lite] GRPO pre-commit 2: Refactor RemoteSGLangEngine thread and SGLang configuration

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/355?tab=commit

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


* .
* .
* .
* .
* .
* .
* fix
* .

* PullRequest: 357 [lite] GRPO pre-commit 3: Fix typos and experiment utilities

Merge branch fw/lite-fix2 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/357?tab=comment

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


* .
* .
* .
* .
* .
* fix destroy process group

* PullRequest: 358 [lite] Support GRPO training locally with the GSM8k dataset

Merge branch fw/lite-fix3 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/358

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


* .
* .
* .
* .
* fix loss mask
* fix
* .

* PullRequest: 368 [lite] Refactor train engine after merging contributions from GitHub

Merge branch fw/lite-train-engine of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/368

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


* .
* .

* PullRequest: 371 [lite] [fix] fix misc bugs in GRPO implementation

Merge branch fw/lite-fix0716 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/371

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


* .

* PullRequest: 370 [lite] Add Slurm Launcher and Ray Launcher

Merge branch mzy/lite/launcher of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/370

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


* .
* .
* .
* fix

* PullRequest: 392 [lite] Fix several bugs regarding RL learning and add an example to reproduce boba-math results.

Merge branch fw/lite-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/392

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
* .
* qwen2 grpo works
* fix
* fix
* async works
* fix
* slurm launcher not tested
* fix arg parse
* .
* sglang server wrapper
* .
* .
* slurm run
* ready for boba
* debug
* 32k run
* .
* .
* fix
* .
* .
* .
* .
* .
* fix
* .
* fix
* .
* .
* .
* .
* fix
* .
* .
* .
* .
* .
* .
* .
* refactor train engine
* refactor train engine
* .
* fix update weight error
* .
* .
* match train
* format
* .
* fix
* seems to work
* .
* .
* .
* .

* .

* PullRequest: 408 [Feature] Bump SGLang version to v0.4.9.post2

Merge branch fw/sgl049 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/408

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


* .
* bump arealite to sglang 0.4.9.post2
* .
* PullRequest: 412 [lite] Minor refactor on `UpdateWeightMeta`

* PullRequest: 422 [lite] Fix tests and scripts after updating sgl to 0.4.9

Merge branch fw/sgl049 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/422

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


* .
* bump arealite to sglang 0.4.9.post2
* .
* PullRequest: 412 [lite] Minor refactor on `UpdateWeightMeta`
* .

* PullRequest: 423 [lite] Remove the boba example for github release.

Merge branch fw/remove-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/423

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


* .
* .

* update readme

* .

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
 2025-07-24 19:24:14 +08:00
朱晗 84e2d75a0d Merge remote-tracking branch 'backup/lite' into lcy/refactor 2025-07-24 15:37:37 +08:00
Wei Fu 311bcd7697
[lite] [feature] Bump to SGLang v0.4.9.post2 and use NCCL to update weights (#196) 
* PullRequest: 353 [Lite] Add gradient checkpointing to FSDPEngine

Merge branch mzy/add-gradient-ckpt of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/353

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


* add gradient checkpointing

* PullRequest: 354 [lite] GRPO pre-commit: minor changes in FSDP  engine

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/354

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


* .
* .
* .
* .

* PullRequest: 355 [Lite] GRPO pre-commit 2: Refactor RemoteSGLangEngine thread and SGLang configuration

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/355?tab=commit

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


* .
* .
* .
* .
* .
* .
* fix
* .

* PullRequest: 357 [lite] GRPO pre-commit 3: Fix typos and experiment utilities

Merge branch fw/lite-fix2 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/357?tab=comment

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


* .
* .
* .
* .
* .
* fix destroy process group

* PullRequest: 358 [lite] Support GRPO training locally with the GSM8k dataset

Merge branch fw/lite-fix3 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/358

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


* .
* .
* .
* .
* fix loss mask
* fix
* .

* PullRequest: 368 [lite] Refactor train engine after merging contributions from GitHub

Merge branch fw/lite-train-engine of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/368

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


* .
* .

* PullRequest: 371 [lite] [fix] fix misc bugs in GRPO implementation

Merge branch fw/lite-fix0716 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/371

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


* .

* PullRequest: 370 [lite] Add Slurm Launcher and Ray Launcher

Merge branch mzy/lite/launcher of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/370

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


* .
* .
* .
* fix

* PullRequest: 392 [lite] Fix several bugs regarding RL learning and add an example to reproduce boba-math results.

Merge branch fw/lite-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/392

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
* .
* qwen2 grpo works
* fix
* fix
* async works
* fix
* slurm launcher not tested
* fix arg parse
* .
* sglang server wrapper
* .
* .
* slurm run
* ready for boba
* debug
* 32k run
* .
* .
* fix
* .
* .
* .
* .
* .
* fix
* .
* fix
* .
* .
* .
* .
* fix
* .
* .
* .
* .
* .
* .
* .
* refactor train engine
* refactor train engine
* .
* fix update weight error
* .
* .
* match train
* format
* .
* fix
* seems to work
* .
* .
* .
* .

* .

* PullRequest: 408 [Feature] Bump SGLang version to v0.4.9.post2

Merge branch fw/sgl049 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/408

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


* .
* bump arealite to sglang 0.4.9.post2
* .
* PullRequest: 412 [lite] Minor refactor on `UpdateWeightMeta`

* PullRequest: 422 [lite] Fix tests and scripts after updating sgl to 0.4.9

Merge branch fw/sgl049 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/422

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


* .
* bump arealite to sglang 0.4.9.post2
* .
* PullRequest: 412 [lite] Minor refactor on `UpdateWeightMeta`
* .

* PullRequest: 423 [lite] Remove the boba example for github release.

Merge branch fw/remove-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/423

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


* .
* .

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
 2025-07-24 15:34:52 +08:00
朱晗 5118cfaea2 0724_merge3 2025-07-24 15:22:12 +08:00
朱晗 176ec4bb23 0724_merge3 2025-07-24 14:29:29 +08:00
朱晗 c816a3ce44 0724_merge1 2025-07-24 14:18:42 +08:00
lichangye.lcy 6c28d52387 0724_1 2025-07-24 13:30:20 +08:00
朱晗 9a166053ee 0724_1 2025-07-24 11:15:54 +08:00
朱晗 00b5d878b3 0723_reformatted_5 2025-07-23 17:13:49 +08:00
lichangye.lcy 9ec2c3f640 0723_1 2025-07-23 16:54:17 +08:00
朱晗 6bde86a934 reformatted 2025-07-23 13:58:25 +08:00
朱晗 eff8f09149 0723_1 2025-07-23 11:02:36 +08:00
lichangye.lcy ea12141f2b 0722_4 2025-07-22 16:03:29 +08:00
lichangye.lcy 229f101b44 0722_4 2025-07-22 15:58:19 +08:00
Wei Fu 6239633213
[doc] [lite] Add customization docs for AReaLite. (#191) 
* PullRequest: 353 [Lite] Add gradient checkpointing to FSDPEngine

Merge branch mzy/add-gradient-ckpt of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/353

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


* add gradient checkpointing

* PullRequest: 354 [lite] GRPO pre-commit: minor changes in FSDP  engine

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/354

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


* .
* .
* .
* .

* PullRequest: 355 [Lite] GRPO pre-commit 2: Refactor RemoteSGLangEngine thread and SGLang configuration

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/355?tab=commit

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


* .
* .
* .
* .
* .
* .
* fix
* .

* PullRequest: 357 [lite] GRPO pre-commit 3: Fix typos and experiment utilities

Merge branch fw/lite-fix2 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/357?tab=comment

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


* .
* .
* .
* .
* .
* fix destroy process group

* PullRequest: 358 [lite] Support GRPO training locally with the GSM8k dataset

Merge branch fw/lite-fix3 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/358

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


* .
* .
* .
* .
* fix loss mask
* fix
* .

* PullRequest: 368 [lite] Refactor train engine after merging contributions from GitHub

Merge branch fw/lite-train-engine of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/368

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


* .
* .

* PullRequest: 371 [lite] [fix] fix misc bugs in GRPO implementation

Merge branch fw/lite-fix0716 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/371

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


* .

* PullRequest: 370 [lite] Add Slurm Launcher and Ray Launcher

Merge branch mzy/lite/launcher of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/370

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


* .
* .
* .
* fix

* PullRequest: 392 [lite] Fix several bugs regarding RL learning and add an example to reproduce boba-math results.

Merge branch fw/lite-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/392

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
* .
* qwen2 grpo works
* fix
* fix
* async works
* fix
* slurm launcher not tested
* fix arg parse
* .
* sglang server wrapper
* .
* .
* slurm run
* ready for boba
* debug
* 32k run
* .
* .
* fix
* .
* .
* .
* .
* .
* fix
* .
* fix
* .
* .
* .
* .
* fix
* .
* .
* .
* .
* .
* .
* .
* refactor train engine
* refactor train engine
* .
* fix update weight error
* .
* .
* match train
* format
* .
* fix
* seems to work
* .
* .
* .
* .

* .

* .

* .

* .

* .

* .

* .

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
 2025-07-22 15:43:31 +08:00
朱晗 eba0b5fd72 0722_3 2025-07-22 15:19:31 +08:00
lichangye.lcy 7199ce25b6 0722_2 2025-07-22 14:55:13 +08:00
lichangye.lcy 3d2f7a9278 Merge branch 'lcy/refactor' of https://code.alipay.com/inclusionAI/AReaL into lcy/refactor 2025-07-22 11:10:45 +08:00
朱晗 79e2a81762 0722_1 2025-07-22 11:09:24 +08:00
朱晗 80862b7016 0721_8 2025-07-21 18:30:47 +08:00
朱晗 f451dbd692 0721_merge7 2025-07-21 18:10:24 +08:00
朱晗 c29561498e 0721_merge6 2025-07-21 17:57:29 +08:00
朱晗 b4e8215f55 0721_merge5 2025-07-21 17:17:32 +08:00
朱晗 a2d6d21810 0721_merge4 2025-07-21 17:02:32 +08:00
朱晗 60ac722779 0721_merge3 2025-07-21 16:58:42 +08:00
lichangye.lcy 339e87ab80 0721_formal 2025-07-21 16:52:00 +08:00
lichangye.lcy 9fcc177237 0721_4 2025-07-21 13:28:23 +08:00
Wei Fu 4804b05637
[Refactor] Rename files in arealite before release. (#190) 
* PullRequest: 353 [Lite] Add gradient checkpointing to FSDPEngine

Merge branch mzy/add-gradient-ckpt of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/353

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


* add gradient checkpointing

* PullRequest: 354 [lite] GRPO pre-commit: minor changes in FSDP  engine

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/354

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


* .
* .
* .
* .

* PullRequest: 355 [Lite] GRPO pre-commit 2: Refactor RemoteSGLangEngine thread and SGLang configuration

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/355?tab=commit

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


* .
* .
* .
* .
* .
* .
* fix
* .

* PullRequest: 357 [lite] GRPO pre-commit 3: Fix typos and experiment utilities

Merge branch fw/lite-fix2 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/357?tab=comment

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


* .
* .
* .
* .
* .
* fix destroy process group

* PullRequest: 358 [lite] Support GRPO training locally with the GSM8k dataset

Merge branch fw/lite-fix3 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/358

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


* .
* .
* .
* .
* fix loss mask
* fix
* .

* PullRequest: 368 [lite] Refactor train engine after merging contributions from GitHub

Merge branch fw/lite-train-engine of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/368

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


* .
* .

* PullRequest: 371 [lite] [fix] fix misc bugs in GRPO implementation

Merge branch fw/lite-fix0716 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/371

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


* .

* PullRequest: 370 [lite] Add Slurm Launcher and Ray Launcher

Merge branch mzy/lite/launcher of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/370

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


* .
* .
* .
* fix

* PullRequest: 392 [lite] Fix several bugs regarding RL learning and add an example to reproduce boba-math results.

Merge branch fw/lite-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/392

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
* .
* qwen2 grpo works
* fix
* fix
* async works
* fix
* slurm launcher not tested
* fix arg parse
* .
* sglang server wrapper
* .
* .
* slurm run
* ready for boba
* debug
* 32k run
* .
* .
* fix
* .
* .
* .
* .
* .
* fix
* .
* fix
* .
* .
* .
* .
* fix
* .
* .
* .
* .
* .
* .
* .
* refactor train engine
* refactor train engine
* .
* fix update weight error
* .
* .
* match train
* format
* .
* fix
* seems to work
* .
* .
* .
* .

* format

* format

* .

* rename

* rename

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
 2025-07-21 12:57:50 +08:00
Wei Fu 18f8a056b6
[Feature] [lite] Merge from internal dev repo (#189) 
* PullRequest: 353 [Lite] Add gradient checkpointing to FSDPEngine

Merge branch mzy/add-gradient-ckpt of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/353

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


* add gradient checkpointing

* PullRequest: 354 [lite] GRPO pre-commit: minor changes in FSDP  engine

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/354

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


* .
* .
* .
* .

* PullRequest: 355 [Lite] GRPO pre-commit 2: Refactor RemoteSGLangEngine thread and SGLang configuration

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/355?tab=commit

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


* .
* .
* .
* .
* .
* .
* fix
* .

* PullRequest: 357 [lite] GRPO pre-commit 3: Fix typos and experiment utilities

Merge branch fw/lite-fix2 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/357?tab=comment

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


* .
* .
* .
* .
* .
* fix destroy process group

* PullRequest: 358 [lite] Support GRPO training locally with the GSM8k dataset

Merge branch fw/lite-fix3 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/358

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


* .
* .
* .
* .
* fix loss mask
* fix
* .

* PullRequest: 368 [lite] Refactor train engine after merging contributions from GitHub

Merge branch fw/lite-train-engine of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/368

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


* .
* .

* PullRequest: 371 [lite] [fix] fix misc bugs in GRPO implementation

Merge branch fw/lite-fix0716 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/371

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


* .

* PullRequest: 370 [lite] Add Slurm Launcher and Ray Launcher

Merge branch mzy/lite/launcher of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/370

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


* .
* .
* .
* fix

* PullRequest: 392 [lite] Fix several bugs regarding RL learning and add an example to reproduce boba-math results.

Merge branch fw/lite-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/392

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
* .
* qwen2 grpo works
* fix
* fix
* async works
* fix
* slurm launcher not tested
* fix arg parse
* .
* sglang server wrapper
* .
* .
* slurm run
* ready for boba
* debug
* 32k run
* .
* .
* fix
* .
* .
* .
* .
* .
* fix
* .
* fix
* .
* .
* .
* .
* fix
* .
* .
* .
* .
* .
* .
* .
* refactor train engine
* refactor train engine
* .
* fix update weight error
* .
* .
* match train
* format
* .
* fix
* seems to work
* .
* .
* .
* .

* format

* format

* .

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
 2025-07-21 12:52:43 +08:00
博惟 9c4da33f61 Merge branch 'lite' of https://github.com/inclusionAI/AReaL into lite 2025-07-21 12:44:55 +08:00
Night f68a4f677d
Implement fsdp distributed update (#183) 
* PullRequest: 353 [Lite] Add gradient checkpointing to FSDPEngine

Merge branch mzy/add-gradient-ckpt of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/353

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


* add gradient checkpointing

* PullRequest: 354 [lite] GRPO pre-commit: minor changes in FSDP  engine

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/354

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


* .
* .
* .
* .

* PullRequest: 355 [Lite] GRPO pre-commit 2: Refactor RemoteSGLangEngine thread and SGLang configuration

Merge branch fw/lite-fix1 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/355?tab=commit

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


* .
* .
* .
* .
* .
* .
* fix
* .

* PullRequest: 357 [lite] GRPO pre-commit 3: Fix typos and experiment utilities

Merge branch fw/lite-fix2 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/357?tab=comment

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


* .
* .
* .
* .
* .
* fix destroy process group

* PullRequest: 358 [lite] Support GRPO training locally with the GSM8k dataset

Merge branch fw/lite-fix3 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/358

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


* .
* .
* .
* .
* fix loss mask
* fix
* .

* PullRequest: 368 [lite] Refactor train engine after merging contributions from GitHub

Merge branch fw/lite-train-engine of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/368

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


* .
* .

* PullRequest: 371 [lite] [fix] fix misc bugs in GRPO implementation

Merge branch fw/lite-fix0716 of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/371

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


* .

* added remote nccl weight update

feat: implement update_weights_from_distributed in fsdp_engine.py

unfinishd test, raise PR first

coroutine for each server

chore: change uploads weights behavior, change test order

fix small bug

fixed test

* fix rebase

* add test.sh

* updated, test stil fails

* .

* .

* .

* fix: full_tensor() should happen in all rank (#187)

Co-authored-by: ChangyiYang <changyiyang2023@gmail.com>

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
Co-authored-by: 博惟 <bowei.fw@antgroup.com>
Co-authored-by: ChangyiYang <changyiyang2023@gmail.com>
Co-authored-by: ChangyiYang <112288487+ChangyiYang@users.noreply.github.com>
 2025-07-21 12:42:00 +08:00
朱晗 8f263713eb merge_0721_2 2025-07-21 11:42:18 +08:00
朱晗 a157510799 0721_3 2025-07-21 11:34:28 +08:00
博惟 2f1b679ad6 PullRequest: 392 [lite] Fix several bugs regarding RL learning and add an example to reproduce boba-math results. 
Merge branch fw/lite-boba of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/392

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
* .
* qwen2 grpo works
* fix
* fix
* async works
* fix
* slurm launcher not tested
* fix arg parse
* .
* sglang server wrapper
* .
* .
* slurm run
* ready for boba
* debug
* 32k run
* .
* .
* fix
* .
* .
* .
* .
* .
* fix
* .
* fix
* .
* .
* .
* .
* fix
* .
* .
* .
* .
* .
* .
* .
* refactor train engine
* refactor train engine
* .
* fix update weight error
* .
* .
* match train
* format
* .
* fix
* seems to work
* .
* .
* .
* .
 2025-07-21 11:26:36 +08:00
lichangye.lcy 25b65a2119 0721_1 2025-07-21 11:16:51 +08:00
朱晗 ade6a1d95c Merge remote-tracking branch 'origin/lite' into lcy/refactor 2025-07-21 10:31:13 +08:00
晓雷 ddabd9cc9d PullRequest: 370 [lite] Add Slurm Launcher and Ray Launcher 
Merge branch mzy/lite/launcher of git@code.alipay.com:inclusionAI/AReaL.git into lite
https://code.alipay.com/inclusionAI/AReaL/pull_requests/370

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


* .
* .
* .
* fix
 2025-07-21 10:29:51 +08:00