cncjs VS candle

I believe the Tool Change command is supported by: gSender or cncjs.

Get a raspberry pi, https://www.raspberrypi.org/, throw UGS https://winder.github.io/ugs_website/ or cnc.js https://cnc.js.org/ on it.

I use https://cnc.js.org/ to send g-code to the machine, this uses web page interface to set up the machine.

https://github.com/cncjs/cncjs/issues/431 ?

CNCjs - For CNC, same as above but for my CNC router, though I would never trust my CNC to run when I'm not physically close by ha ha so this hasn't been exposed to my OpenZiti network.

I think cncjs is what you're looking for: https://cnc.js.org/

Can you try with a different gcode sender software (cncjs), to see if you can Reset (red button) and Unlock (orange button)?

6 - Alternative, Save the gcode and use a g-code sender (example: cncjs). Notice: a g-code sender needs to know where is the 0,0 position/the start position, so in LightBurn select the start position "Current Position" and select the appropriate Job Origin. Save the gcode. On cncjs, move the laser to the "Job Origin" and zero both X and Y (the icon after the + on the Work Position). Click the blue Upload G-Code button, select your file and press the Play button to start the job.

Software: bCNC, cncjs, a couple others

Candle already exists[1], and it runs pretty well. Can use both CUDA and Metal backends (or just plain-old CPU).

[1] https://github.com/huggingface/candle

Check out Candle! It's a Deep Learning framework for Rust. You can run LLMs in binaries.

Kalosm is a meta-framework for AI written in Rust using candle. Kalosm supports local quantized large language models like Llama, Mistral, Phi-1.5, and Zephyr. It also supports other quantized models like Wuerstchen, Segment Anything, and Whisper. In addition to local models, Kalosm supports remote models like GPT-4 and ada embeddings.

I have been working on a machine learning library called candle-lora for Candle. It implementes a technique called LoRA (low rank adaptation), which allows you to reduce a model's trainable parameter count by wrapping and freezing old layers.

[2] https://github.com/huggingface/candle/issues/313

We provide full local inference in browser, by using libraries from Hugging Face like transformers.js or candle for WASM inference.

We've first announced Candle, a minimalist ML framework in Rust 6 weeks ago. Since then we've focused on adding various recent models and improved the framework so as to support the necessary features in an efficient way. You can checkout a gallery of the examples, supported models include:

How did you select those two as your options?

I'm just a hobbyist that enjoys programming, and I eventually wanted to expand beyond python. I looked at Haskell and read Learn You a Haskell and did some Exercism exercises but never got anywhere close to being able to use it for real projects. Have been trying to learn about Lisp lately and feel like I've come to a similar dead end.

On the other hand, both Go and Rust have felt fulfilling and practical, with static typing and solid tooling, cross compilations, static binaries, and dependency management that is just a huge breath of fresh air coming from python.

The ML / data science scene is nowhere near as developed as in Python, and I still lean on jupyter/polars/PyTorch here, but I think the candle project[0] seems very interesting. Compiling whisper down to a single CUDA-leveraging binary for fast local transcription is pretty cool!

[0]: https://github.com/huggingface/candle