Yuge Zhang

Results 279 comments of Yuge Zhang

I didn't see the OOM issue from this log. Do you have more contexts to help us investigate?

Qwen2.5VL is known to be problematic with current VERL integration. The major problem is we didn't upgrade our VERL integration after VERL has upgraded themselves. Related to #105

Looks reasonable. Would you feel that `` is enough for you? Getting children components in react has been always tricky and it's unclear whether the diff should be based on...

If you are running with v0.2.2, you should check out examples from v0.2.2: https://github.com/microsoft/agent-lightning/tree/v0.2.2/examples

This is a breaking change that requires much effort.

So you want to remove the thinking tokens from the response for training? I think that will cause discrepency between training and inference.

Has verl figured that out? If they haven't, we are unable to help despite we want to.

I think this is a known issue. Remember what rollout IDs have been sent and reject those unregistered rollouts might be a workaround. In the long run, we need to...