草原狼

Windows PowerShell displays "Error code: Wsl/0x80070424" after the computer is restarted.

Docker Desktop is not starting properly.

2

### Description running engine: waiting for the VM setup to be ready: running filesharing: running virtiofsd for /home: exit status 101 ### Reproduce /opt/docker-desktop/bin/docker-desktop ### Expected behavior _No response_ ###...

mindnlp 怎么指定调用npu呢

2

mindnlp 怎么指定调用npu呢？ 也是类似 torch 么？ import torch from transformers import AutoModelForCausalLM, AutoTokenizer, LlamaForCausalLM tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b") with torch.device("cuda"): model = AutoModelForCausalLM.from_pretrained( "tiiuae/falcon-7b", torch_dtype=torch.float16, use_flash_attention_2=True, )

1.32.0 使用 helm 安装cilium 报错

3

# 安装cilium # 添加源 helm repo add cilium https://helm.cilium.io # 修改为国内源 helm pull cilium/cilium tar xvf cilium-*.tgz cd cilium/ sed -i "s#quay.io/#quay.m.daocloud.io/#g" values.yaml helm install cilium ./cilium/ -n kube-system 以上安装过程会报错

I have some permission authentication in my k8s. How should I modify the $HOME/.config/helm file? I didn't find it in the official documentation（https://helm.sh/zh/docs/helm/helm/）. Thank you very much for your help.

如何直接使用模型参数启动模型呢

3

以 qwen2.5 为例，观察到咱参数都是通过 huggingface 直接拉取的方式来实现的，能否给定模型参数的地址运行此模型 qwen2.5-7b-instruct-l4: enabled: false url: "hf://Qwen/Qwen2.5-7B-Instruct" features: [TextGeneration] env: VLLM_ATTENTION_BACKEND: "FLASHINFER" # VLLM_USE_V1: "1" args: - --max-model-len=8192 - --max-num-batched-token=8192 - --max-num-seqs=256 - --gpu-memory-utilization=0.95 - --kv-cache-dtype=fp8 -...