Chris Braddock

Honestly I wasn't able to see where the CR exists in the code. Maybe it's introduced pushing to npm? That said, I'm not sure if [this](https://github.com/chrisbraddock/Jsome/commit/75545bf9588229aac3f9fdd480f5b7ad0bd3621e) will help or not.

Same Node 14.20 Win 10. I see there is #2729.

Me as well. Windows. Node 14.17.3.

Any issues related to #4431? I finally just got `--tensor-parallel-size 2` working. Tested against a bunch of models and it's solid.

> @chrisbraddock Could you post minimal working code, please? And also, are running in the official vLLM docker container? If not, how did you install vLLM (from source, from pypi)?...

> @chrisbraddock I got it working in a very similar way (I described it [here](https://github.com/vllm-project/vllm/issues/4431#issuecomment-2095138681)). @RomanKoshkin I was working off some of your info for sure. I didn't quite understand...

This is a good plugin with lots of open PRs and low hanging fruit fixes. I hope it can continue.

gpt-pilot is quite good at this. Try it out to get an idea. I think there are planner and reviewer agents for each step. I kind of wish OpenDevin incorporated...

> In the meantime I've been using a vscode extension called `Settings Sync` I just looked at the issues for that deprecated plugin and that's a no for me. :)...

If I get to it before you, for sure. :)