candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
The MetaVoice-1B model has significant degradation compared to the Python version. I believe one of the main causes is using a 64x smaller decoder model (instead of multiband diffusion and...
llama.cpp now supports grammars: https://til.simonwillison.net/llms/llama-cpp-python-grammars Is that something that will come to candle? It sounds like the approach taken in this python library would be straight forward: https://github.com/1rgs/jsonformer/blob/main/jsonformer/main.py Basically, since...
When I run gemma example using the command line on my mac, I get the following error. It looks like this is a compilation error with some package. runtime errors:...
It would be awesome to have some issue labelling for new contributors to get a start.
I found the mixtral example in this repo, and try to run it on A100 80GB, but the default Mixtral-8x7B-v0.1 runs out of memory. I was curious what GPU can...
I'm trying to use Flash Attention on an environment with CUDA 12.1 but it fails to compile. Is it expected? Reproducing: 1. Start a Docker container with CUDA version 12.1.1...
Hi I have these errors and my code tries to even retry but there seems to be an issue when I try to continuously use the gemma and mistral examples...
This PR allows user to merge two `GradStore`s together (and also to create an empty one). It is helpful for collecting gradients from multiple different backward passes (e.g. with different...
while pytoch's clone return contiguous tensor candle ```rust #[test] fn test_copy1() -> candle::Result { let device = candle::Device::Cpu; let test = Tensor::zeros((2, 10), DType::U32, &device)?; let test1 = test.narrow(1, 0,...
