From e230bb18961422d58e8ef2decea94372aba7b21f Mon Sep 17 00:00:00 2001 From: pxc Date: Wed, 20 Aug 2025 19:17:26 +0800 Subject: [PATCH 1/3] minor fix of plugin loader --- trinity/trainer/verl/dp_actor.py | 2 -- trinity/utils/plugin_loader.py | 5 ++++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/trinity/trainer/verl/dp_actor.py b/trinity/trainer/verl/dp_actor.py index 4eafcb95a9..8092d0a7ca 100644 --- a/trinity/trainer/verl/dp_actor.py +++ b/trinity/trainer/verl/dp_actor.py @@ -35,7 +35,6 @@ from trinity.algorithm.kl_fn.kl_fn import DummyKLFn from trinity.algorithm.utils import prefix_metrics from trinity.common.config import AlgorithmConfig -from trinity.utils.plugin_loader import load_plugins __all__ = ["DataParallelPPOActor"] @@ -49,7 +48,6 @@ def __init__( ): """When optimizer is None, it is Reference Policy""" super().__init__(config, actor_module, actor_optimizer) - load_plugins() self.policy_loss_fn = None self.kl_loss_fn = None self.entropy_loss_fn = None diff --git a/trinity/utils/plugin_loader.py b/trinity/utils/plugin_loader.py index d67b43c332..097cbe2084 100644 --- a/trinity/utils/plugin_loader.py +++ b/trinity/utils/plugin_loader.py @@ -46,7 +46,10 @@ def load_plugin_from_dirs(plugin_dirs: Union[str, List[str]]) -> None: continue logger.info(f"Loading plugin modules from [{file}]...") # load modules from file - load_from_file(os.path.join(plugin_dir, file)) + try: + load_from_file(os.path.join(plugin_dir, file)) + except Exception as e: + logger.error(f"Failed to load plugin from {file}: {e}") def load_from_file(file_path: str): From 965760d45421ead40375f3a3db728cf585aed186 Mon Sep 17 00:00:00 2001 From: pxc Date: Wed, 20 Aug 2025 19:23:38 +0800 Subject: [PATCH 2/3] update readme --- README.md | 1 + README_zh.md | 1 + docs/sphinx_doc/source/main.md | 1 + 3 files changed, 3 insertions(+) diff --git a/README.md b/README.md index 5be6a79e5d..16c70c3964 100644 --- a/README.md +++ b/README.md @@ -22,6 +22,7 @@ ## 🚀 News +* [2025-08] Trinity-RFT v0.2.1 is released. * [2025-08] We now support training on general multi-step workflows! Please check out examples for [ALFWorld](./docs/sphinx_doc/source/tutorial/example_step_wise.md) and [ReAct](./docs/sphinx_doc/source/tutorial/example_react.md). * [2025-07] Trinity-RFT v0.2.0 is released. * [2025-07] We update the [technical report](https://arxiv.org/abs/2505.17826) (arXiv v2) with new features, examples, and experiments. diff --git a/README_zh.md b/README_zh.md index 5da07c561c..60181c546d 100644 --- a/README_zh.md +++ b/README_zh.md @@ -22,6 +22,7 @@ ## 🚀 最新动态 +* [2025-08] 发布 Trinity-RFT v0.2.1 版本，强化了 Agentic RL 和 异步 RL 相关功能。 * [2025-08] Trinity-RFT 现在已经支持通用多轮工作流的训练了，请参考 [ALFWorld](./docs/sphinx_doc/source/tutorial/example_step_wise.md) 和 [ReAct](./docs/sphinx_doc/source/tutorial/example_react.md) 的例子！ * [2025-07] 发布 Trinity-RFT v0.2.0 版本，新增了多项功能优化。 * [2025-07] 更新了[技术报告](https://arxiv.org/abs/2505.17826) (arXiv v2)，增加了新功能、示例和实验。 diff --git a/docs/sphinx_doc/source/main.md b/docs/sphinx_doc/source/main.md index a8d42640f6..2a177ab6e4 100644 --- a/docs/sphinx_doc/source/main.md +++ b/docs/sphinx_doc/source/main.md @@ -8,6 +8,7 @@ ## 🚀 News +* [2025-08] Trinity-RFT v0.2.1 is released. * [2025-08] We now support training on general multi-step workflows! Please check out examples for [ALFWorld](./docs/sphinx_doc/source/tutorial/example_step_wise.md) and [ReAct](./docs/sphinx_doc/source/tutorial/example_react.md). * [2025-07] Trinity-RFT v0.2.0 is released. * [2025-07] We update the [technical report](https://arxiv.org/abs/2505.17826) (arXiv v2) with new features, examples, and experiments. From 81923cf1f3aa4a657f2d34047ad558ca576240be Mon Sep 17 00:00:00 2001 From: pxc Date: Wed, 20 Aug 2025 19:39:39 +0800 Subject: [PATCH 3/3] update news --- README.md | 3 ++- README_zh.md | 3 ++- docs/sphinx_doc/source/main.md | 3 ++- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 16c70c3964..eac297c97b 100644 --- a/README.md +++ b/README.md @@ -22,7 +22,8 @@ ## 🚀 News -* [2025-08] Trinity-RFT v0.2.1 is released. +* [2025-08] ✨ Trinity-RFT v0.2.1 is released with enhanced features for Agentic RL and Async RL. +* [2025-08] 🎵 We introduce [CHORD](https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord), a dynamic integration of SFT and RL for enhanced LLM fine-tuning ([paper](https://arxiv.org/pdf/2508.11408)). * [2025-08] We now support training on general multi-step workflows! Please check out examples for [ALFWorld](./docs/sphinx_doc/source/tutorial/example_step_wise.md) and [ReAct](./docs/sphinx_doc/source/tutorial/example_react.md). * [2025-07] Trinity-RFT v0.2.0 is released. * [2025-07] We update the [technical report](https://arxiv.org/abs/2505.17826) (arXiv v2) with new features, examples, and experiments. diff --git a/README_zh.md b/README_zh.md index 60181c546d..b65dae1006 100644 --- a/README_zh.md +++ b/README_zh.md @@ -22,7 +22,8 @@ ## 🚀 最新动态 -* [2025-08] 发布 Trinity-RFT v0.2.1 版本，强化了 Agentic RL 和 异步 RL 相关功能。 +* [2025-08] ✨ 发布 Trinity-RFT v0.2.1 版本，强化了 Agentic RL 和 异步 RL 相关功能。 +* [2025-08] 🎵 我们推出了 [CHORD](https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord)，一种动态整合 SFT 和 RL 来微调 LLM 的方法（[论文](https://arxiv.org/pdf/2508.11408)）。 * [2025-08] Trinity-RFT 现在已经支持通用多轮工作流的训练了，请参考 [ALFWorld](./docs/sphinx_doc/source/tutorial/example_step_wise.md) 和 [ReAct](./docs/sphinx_doc/source/tutorial/example_react.md) 的例子！ * [2025-07] 发布 Trinity-RFT v0.2.0 版本，新增了多项功能优化。 * [2025-07] 更新了[技术报告](https://arxiv.org/abs/2505.17826) (arXiv v2)，增加了新功能、示例和实验。 diff --git a/docs/sphinx_doc/source/main.md b/docs/sphinx_doc/source/main.md index 2a177ab6e4..f5555d4a37 100644 --- a/docs/sphinx_doc/source/main.md +++ b/docs/sphinx_doc/source/main.md @@ -8,7 +8,8 @@ ## 🚀 News -* [2025-08] Trinity-RFT v0.2.1 is released. +* [2025-08] ✨ Trinity-RFT v0.2.1 is released with enhanced features for Agentic RL and Async RL. +* [2025-08] 🎵 We introduce [CHORD](https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord), a dynamic integration of SFT and RL for enhanced LLM fine-tuning ([paper](https://arxiv.org/pdf/2508.11408)). * [2025-08] We now support training on general multi-step workflows! Please check out examples for [ALFWorld](./docs/sphinx_doc/source/tutorial/example_step_wise.md) and [ReAct](./docs/sphinx_doc/source/tutorial/example_react.md). * [2025-07] Trinity-RFT v0.2.0 is released. * [2025-07] We update the [technical report](https://arxiv.org/abs/2505.17826) (arXiv v2) with new features, examples, and experiments.