AReaL/realhf/base
Wei Fu 29e164a69d
[Fix] [lite] Merge from the internal repo to fix GRPO bugs and refactor the train engine (#181)
* 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>


* .

---------

Co-authored-by: 晓雷 <meizhiyu.mzy@antgroup.com>
2025-07-16 17:26:49 +08:00
..
__init__.py [Feature & Doc & Bug Fix] Add docs, simplified ray-based scripts, and fix issues to stablize asynchronous experiments (#52) 2025-05-28 19:18:05 +08:00
cluster.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
constants.py [Fix] Merge error fixes. (#152) 2025-07-07 10:30:27 +08:00
datapack.py PullRequest: 33 Force the partition to be balanced when the capacity is a large number 2025-03-17 10:47:29 +08:00
gpu_utils.py Support asynchronous RL training, Qwen3, and the latest SGLang (#47) 2025-05-26 09:45:13 +08:00
importing.py Initial commit. 2025-02-24 18:58:19 +08:00
logging.py [Fix] Fix yaml configurations for v0.2 experiments. (#129) 2025-06-24 13:48:02 +08:00
monitor.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
name_resolve.py [Fix] [lite] Merge from the internal repo to fix GRPO bugs and refactor the train engine (#181) 2025-07-16 17:26:49 +08:00
names.py PullRequest: 332 [lite] Support FSDP engines 2025-07-09 16:24:25 +08:00
network.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
numpy_utils.py Initial commit. 2025-02-24 18:58:19 +08:00
pkg_version.py PullRequest: 61 [Patch v0.2.0] Fix the PPO bug in old environments. 2025-03-28 09:58:26 +08:00
prologue.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
ray_utils.py Initial commit. 2025-02-24 18:58:19 +08:00
recover.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
saveload_utils.py Initial commit. 2025-02-24 18:58:19 +08:00
security.py Initial commit. 2025-02-24 18:58:19 +08:00
seeding.py Merge updates from ant repository. (#34) 2025-04-27 11:09:25 +08:00
slurm_utils.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
stats_tracker.py PullRequest: 340 [lite] Refactor trainer API into utilities and remove mb_spec in engine methods 2025-07-10 11:10:10 +08:00
testing.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00
timeutil.py PullRequest: 21 fix timeutil consistency during recover 2025-03-10 16:27:55 +08:00
topology.py PullRequest: 252 [Feature] Fix constants initialization. (#122) 2025-06-23 12:52:49 +08:00