mirror of https://github.com/hpcaitech/ColossalAI.git synced 2026-07-16 17:16:14 +00:00

Files

Tong Li aca547623f [feat] Support prompt level dynamic (#6300 )

* adjust to dynamic prompt bs

* remove debug

* update pad seq (#6303)

Co-authored-by: Tong Li <tong.li35271158@gmail.com>

* adjust to dynamic prompt bs

* remove debug

* fix dp issue

* fix

* fix default settings

---------

Co-authored-by: Tong Li <tong.li35271158@gmail.com>

2025-05-14 16:40:35 +08:00

reward

[fix] revert reward update and evaluation (#6295 )

2025-05-07 10:56:47 +08:00

__init__.py

[chat] add distributed impl (#6210 )

2025-02-21 15:24:23 +08:00

comm.py

[chat] add distributed impl (#6210 )

2025-02-21 15:24:23 +08:00

consumer.py

[feat] Support prompt level dynamic (#6300 )

2025-05-14 16:40:35 +08:00

grpo_consumer.py

[feat] Support prompt level dynamic (#6300 )

2025-05-14 16:40:35 +08:00

inference_backend.py

update pad seq (#6303 )

2025-05-13 16:51:27 +08:00

launch.py

[fix] revert reward update and evaluation (#6295 )

2025-05-07 10:56:47 +08:00

loss.py

[feat] Support DAPO (#6263 )

2025-04-25 17:39:17 +08:00

producer.py

update pad seq (#6303 )

2025-05-13 16:51:27 +08:00

README.md

[chat] add distributed impl (#6210 )

2025-02-21 15:24:23 +08:00

utils.py

update pad seq (#6303 )

2025-05-13 16:51:27 +08:00

README.md

Requirements

pip install cupy-cuda12x
python -m cupyx.tools.install_library --cuda 12.x --library nccl