PyPI page
Home page
Author:
Original author: Bytedance - Seed - MLSys
License:
Apache-2.0
Summary:
Fork of verl: Volcano Engine Reinforcement Learning for LLM
Latest version:
0.5.0.dev2
Required dependencies:
accelerate
|
codetiming
|
datasets
|
dill
|
hydra-core
|
numpy
|
packaging
|
pandas
|
peft
|
pyarrow
|
pybind11
|
pylatexenc
|
ray
|
tensordict
|
torchdata
|
transformers
|
wandb
Optional dependencies:
flash-attn
|
liger-kernel
|
math-verify
|
mathruler
|
mbridge
|
pre-commit
|
py-spy
|
pyext
|
pytest
|
pytest-asyncio
|
qwen_vl_utils
|
sglang
|
tensordict
|
torch
|
torch-memory-saver
|
torchvision
|
trl
|
vllm
Downloads last day:
0
Downloads last week:
14
Downloads last month:
18