agent-lightning
agent-lightning copied to clipboard
microsoft
The absolute trainer to light up AI agents.
Lack of managed service - [ ] Re-ignite conversation with PG about synthetic monitoring managed services for real-user journey. - [ ] Document current workaround using App Insights + Playwright....
Investigate the new Azure App Testing . - [ ] Playwright integration and functional testing at scale. - [ ] Azure Load Testing - [ ] Raise internal awareness
## Summary - add rendering support for the `jinja` and `poml` engines to `PromptTemplate.format` - allow inline POML markup or `.poml` files with configurable output format via `_poml_format` - cover...
## Summary - add a reusable utility for creating, starting, and stopping uvicorn servers in threads or processes - switch the LLM proxy and LightningStore server to use the shared...
full finetune is ok, lora error: (WorkerDict pid=502574) Exception in thread Thread-3 (_loop_forever): (WorkerDict pid=502574) Traceback (most recent call last): (WorkerDict pid=502574) File "/media/hdd4tb/sankuai/env/sk_rl_3.10/lib/python3.10/threading.py", line 1016, in _bootstrap_inner (WorkerDict pid=502574)...
batch data I crashed by many times in batch.to(device) may because fsdp? DataProto(batch=TensorDict( [36m(TaskRunner pid=73703)[0m fields={ [36m(TaskRunner pid=73703)[0m attention_mask: Tensor(shape=torch.Size([56, 16384]), device=cpu, dtype=torch.int64, is_shared=False), [36m(TaskRunner pid=73703)[0m input_ids: Tensor(shape=torch.Size([56, 16384]), device=cpu,...
I noticed that the environment configuration requires torch==2.7, but the latest PyTorch version supported by Ascend 910C is currently 2.6, which means this repository does not currently support Ascend 910C....
It's not working with verl 0.5.0. ```bash ray.exceptions.RayTaskError(ModuleNotFoundError): ray::WorkerDict.actor_rollout_init_model() (pid=10928, ip=10.1.1.104, actor_id=3b846a02a80aa8b92c91fcfb01000000, repr=) File "/usr/lib/python3.12/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result raise self._exception...
According to README, The following versions and installation order have been tested and are confirmed to work. The following version should be understood as a training environment. Is it the...
I have read your paper, which have great help for my work. In your paper, you said that agent-lightning supports multi-agent reinforcement learning with any agent and almost no code...
