yilun wang（王逸伦）

waht' is the rule of autoscaler

1

## Environment details: * local deployment, native ubuntu, Mac OS, Kubernetes, ... * version of docker, ubuntu, ... ## Steps to reproduce the issue: 1. 2. 3. ## Provide the...

Is there some function examples?

1

hi,s8sg, do you already provide some functions,i want to try it!

[Usage]: how to shutdown vllm server

1

### Your current environment ```text The output of `python collect_env.py` ``` ### How would you like to use vllm if i use > vllm serve llm/qwen/Qwen2-0.5B-Instruct how to shutdown vllm...

How to get attention scores

1

Does your codes have function to analyze attention scores, or needs to be observed in the **Transformer** class

for i in range(task_num): # 1. run the i-th task and compute loss for k=0 logits = self.net(x_spt[i], vars=None, bn_training=True) loss = F.cross_entropy(logits, y_spt[i]) grad = torch.autograd.grad(loss, self.net.parameters()) fast_weights =...

question about install Holmesgpt in k8s

1

can I directly install Holmesgpt in my k8s cluster with out Robusta, How to send prometheus alert to holmesgpt in the simplest way, just for testing purposes

<install> statefulset , FailedScheduling

19

It it not easy to install `robusta` for me, when I install robusta using helm, they can not start alertmanager-robusta-kube-prometheus-st-alertmanager-0 0/2 Pending 0 18s prometheus-robusta-kube-prometheus-st-prometheus-0 0/2 Pending 0 8s the...