jiadj

The format of sdk-go-Cloudevent (github.com/cloudevents/sdk-go/v2) is now used by most people，at the same time , nuclio also sets a set of cloudevent specifications in `pkg/processor/cloudevent`. I look at source code,...

networkData not effective

1

Recently, I use kubevirt as virtual machine. But after restart machine, I found that ip address cannot be assigned. The default network config: So, I add networkData filed in vm.yaml,...

If third level domain exists, name server will not return second level ip

2

I use etcd as storage and have two record. If `/coredns/com/ttdd1/t1` not exist, `nslookup ttdd1.com` will return 100.100.100.101. if `/coredns/com/ttdd1/t1` exist, `nslookup ttdd1.com` will return 100.100.100.102. if other third level...

Do Ollama support multiple GPUs working simultaneously?

4

I have 8 RTX 4090 GPUs. Can they support a 70B-int4 parameter model?

有没有计划自己训练模型来支持ngql语法

18

我看了下你们langchain的实现，感觉就是一个表通过cypher的prompt来实现，但是感觉在复杂环境下，比如很多节点和边，我用老gpt4（截止日期21年的）获取不到nebula的语法。你们有没有自己训练的模型来支持新的或者复杂的语法

我最近想在项目上用qwen1.5来驱动，但是我不太懂int4量化、int8量化还是16量化他们的差距有多大。有没有关于这方面的文章分析

### What is the issue? 我不太懂推理，假设我有4个gpu，每个24g。我的模型运行起来也需要24g，此时我应该选择多卡还是单卡。单卡使用24g快还是多卡每个使用6g快？ ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_

添加下pylint和setup.cfg来自动化格式代码

I suddenly encountered an error. It was working fine before, but now it shows 'UDF Folder doesn't Exist!'

7

tail -n 100 -f nebula-graphd.ERROR 显示 tail -n 100 -f nebula-graphd.INFO 我没看过之前的日志，他为什么会在nebula用户下

[Bug]: Do paper and law and native layout use the same model for parsing? I noticed that their MD5 values are the same.

5

### Is there an existing issue for the same bug? - [X] I have checked the existing issues. ### Branch name main ### Commit ID main ### Other environment information...