neurallambda

There's work on the transformers main branch that enables Llama.

*Still in Draft* The idea is to have a persistent block of state that the LSP server "owns". This comes from an interest in getting a "Dungeons Master" vibe from...

Dead code, `cache_kwargs`

2

### System Info This is rather low priority. I found it confusing chasing down the occurrences of `cache_kwargs` to try to understand how `sin` and `cos` are getting used in...

(This is a huge tranche of stuff i need to organize)

shell2d makes a circle look low-poly

2

Given this code, I get the following preview/render/stl/print. I thought it might just be a rendering issue, so, I've tracked it at each step including printing, and I'm unsure how...

CUDA not supported. `ValueError: Attempt to split tensors that exceed maximum supported devices. Current LLAMA_MAX_DEVICES=1`

1

This was a problem that I think was prematurely `closed`: https://github.com/abetlen/llama-cpp-python/issues/1166 My current efforts are to get a llama 3.1 70B gguf running on 2 3090s, and no matter my...

Model reloads for every API request, adding additional 15sec to each inference request. Issue with indexing.

4

> This is a critical bug, but probably a quick fix for the devs. > > To get a little more objective, in API mode it's taking ~13-20 seconds for...

Add `esbuild` override: ```json "overrides": { "@libsql/client": "^0.5.3", "esbuild": "0.25.4" }, ``` Update `next` and `wrangler`: ```json "next": "^15.3.2", "wrangler": "^4.14.4" ``` I don't think this breaks anything. There's one...

🐛cloudflared tunnel doesn't work with websockets from Twilio, ngrok *does*

6

**Describe the bug** I cannot connect a Twilio stream via websocket over `cloudflared` to my `wrangler dev` backend locally. This *specific* setup fails, but any other setup works fine!? I'm...