Kebe

Thank you very much for the report, I need to confirm the problem.

Sounds rather unlikely, if it's launching a Pod can it successfully pull the image?

By default, we will only process traffic that contains mesh sidecar, if it is from dockerd, we will not block it. You can try turning on debug mode and checking...

I need LLama3 optimizations from 0.4.1, as well as phi-3-mini support from 0.4.2. See: https://github.com/vllm-project/vllm/releases I have already signed the CLA, and I have had [PR](https://github.com/triton-inference-server/server/pull/6918) merged before.

Can someone please take a look at this PR? Give me some suggestions or feedback?

> Hi @kebe7jun , Could you please let me know if you've already signed a [CLA](https://github.com/triton-inference-server/server/blob/main/CONTRIBUTING.md#contributor-license-agreement-cla)? > > Additionally, Could you please let me know the motivation behind these changes>...

This information is generally associated with users and needs to be able to count the usage of each user. However, Triton does not provide the concept of users, so it...