PyPI page
Home page
Author:
None
License:
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
...
Summary:
siirl: A Decentralized Multi-Agent Reinforcement Learning Framework
Latest version:
0.2.0
Required dependencies:
accelerate
|
codetiming
|
dacite
|
datasets
|
dill
|
fastapi
|
hydra-core
|
imageio
|
loguru
|
math-verify
|
math_verify
|
mathruler
|
numpy
|
packaging
|
pandas
|
peft
|
pyarrow
|
pybind11
|
pylatexenc
|
qwen_vl_utils
|
ray
|
scipy
|
tensorboard
|
tensordict
|
timm
|
torchdata
|
transformers
|
vllm
|
wandb
Optional dependencies:
build
|
flash-attn
|
liger-kernel
|
mathruler
|
pre-commit
|
py-spy
|
pyext
|
pytest
|
ruff
|
sglang
|
tensordict
|
torch
|
torch-memory-saver
|
twine
Downloads last day:
3
Downloads last week:
16
Downloads last month:
38