Shaker Islam

Hi @wagenet @chancancode! I'm really interested in this as well, and I see there's a roadmap item that's maybe related: https://usehelix.com/roadmap#binary-distribution Is there a list of defined tasks to pick...

bump!

Curiously, if you install deps without `installGlobals` and add it back in later, Vite still seems to work!

`@remix-run/node` is included in [`remix-serve`](https://github.com/remix-run/remix/blob/878440781095205487bc735b535ac8bc78740491/packages/remix-serve/package.json#L19) I tried this with `npm` and `npx` and ran into the same problem:

I totally get I don't need to use `installGlobals` here since cloudflare doesn't need it. It just fails without any logs or information as to what to do. My guess...

I have the same issue as @om154. I want to instantiate an API client with environment variables, and instantiate them only once. It's easy to do with `process.env`, but with...

In general it feels like the point is moot - Cloudflare injects the context at request time. So I don't think there's anything we can do here outside of giving...

> I recommend checking out exllamav2, which is becoming more and more popular these days and is much faster than gguf while consuming the same amount of VRAM or less....

a quantized version of CodeLlama would work well locally on macs: https://huggingface.co/TheBloke/CodeLlama-34B-GGUF ollama has a way of interacting with a [quantized CodeLlama](https://ollama.com/library/codellama), but up to the Zed team whether they'd...

> Is llama.cpp actually using Metal? I tried this and noticed (only after enabling some debug logging) that in fact the file `ggml-metal.metal` could not be found (it needs to...