SeibertronSS

The nodeSelector in explainer doesn't work

1

I set the nodeSelector in explainer but it doesn't work.

Cannot get key for artifact location

1

### Environment * How do you deploy Kubeflow Pipelines (KFP)? I deploy the Kubeflow Pipelines (standalone) by Kubeflow Manifests (https://github.com/kubeflow/manifests) * KFP version: 1.7.0 * KFP SDK version: 1.8.2 When...

I found that the default value of the environment variable REVISION_TIMEOUT_SECONDS in the queue-proxy container is 1, which leads to timeouts when I use some models with a long inference...

How do I get the collected measurement records ?

5

Hello everyone, I‘m currently building my own dataset. I want to know how to get the collected measurement records. The device I am using does not match the provided dataset.

Does XGBoost-operator have a python client?

1

Hello, everyone. Does XGBoost-operator have a python client? Just like Pytorch-operator, can XGBoost-operator be run by pythonSDK?

Can PytorchJob skip or cancel the init cantainer?

2

Hello, Dear developers. I encounter a question when using pytorchjob. Can PytorchJob skip or cancel the init cantainer?

I built an LLM inference topology, including preprocessing inference and postprocessing. Each time the inference node only outputs the latest token_id to the postprocessing node, but sometimes the postprocessing node...

I implemented a continuous batching backend in C++, which supports streaming back the results of LLM. However, sometimes when the results of LLM are returned to the postprocessing for decoding,...

Does TensorRT LLM Backend support multi-machine deployment now? Can give an example?

How to write CUDA code in vscode using clangd as LSP

6

I use clangd as the LSP for C/C++ in vscode. Recently, I need to write CUDA. How can I configure clangd as the LSP for cuda in vscode? Especially for...