github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-08-29 13:13:44 +00:00
Code Issues Packages Projects Releases Wiki Activity
grpo-latest-dev-debug
ColossalAI/applications/ColossalChat/coati/distributed
History
YeAnbang 4d18e7d772 spot a possible bug
2025-05-05 18:48:42 +08:00
..
reward fix reward 2025-05-05 15:40:22 +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 fix reward taging bug 2025-05-03 14:34:04 +08:00
grpo_consumer.py fix reward 2025-05-05 15:40:22 +08:00
inference_backend.py spot a possible bug 2025-05-05 18:48:42 +08:00
launch.py small fix 2025-05-03 09:55:24 +08:00
loss.py [feat] Support DAPO (#6263) 2025-04-25 17:39:17 +08:00
producer.py spot a possible bug 2025-05-05 18:48:42 +08:00
README.md [chat] add distributed impl (#6210) 2025-02-21 15:24:23 +08:00
utils.py Support evaluation during training 2025-04-30 18:31:49 +08:00

README.md

Requirements

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