Zoltan Fedor

Hi @marcklingen, Have you had a chance to look into this bug? This bug unfortunately still exists with latest Langfuse version (v2.5.11) Thanks!

I have managed to fix the issue. It turns out it was related to the following:  source: https://langchain-ai.github.io/langgraph/how-tos/streaming-events-from-within-tools/?h=callbacks#define-graph-and-tools Which makes sense. Langfuse is a callback in Langgraph, so if...

I agree with the CLA.

Thanks, @etiennedi, can't wait! It seems (as it was expected) that more and more people are asking for the _class rename_ functionality, for which the _alias_ functionality is an alternative...

+1

+13

thanks @WoosukKwon, unfortunately even without the `--num-scheduler-steps 8` flag it has still failed (although with a different error): ``` │ ERROR 08-30 19:19:10 client.py:412] await self.check_health(socket=socket) │ │ ERROR 08-30...

Two minutes later the next error: ``` │ return self._call_impl(*args, **kwargs) │ │ File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl │ │ return forward_call(*args, **kwargs) │ │ File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/layers/sampler.py", line 110,...

@robertgshaw2-neuralmagic , sorry, we do not have a way to reproduce it either.

There isn't much to share. We are using your docker image from Dockerhub: https://hub.docker.com/r/vllm/vllm-openai/tags No modification, we run it as-is. At the top of this ticket you can see the...