candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
I am trying to run yolov9 exported to onnx (using the export.py script), but I am encountring this error (opset 16): ``` thread 'main' panicked at src/main.rs:33:72: called `Result::unwrap()` on...
Hi, This is my Cargo.toml: ``` [package] name = "myapp" version = "0.1.0" edition = "2021" [dependencies] candle-core = { git = "https://github.com/huggingface/candle.git", version = "0.5.0", features = ["cuda"] }...
I have: 4x RTX 3080 = 40GB total memory (each GPU by 10 GB memory) I try to load model Mistral 7 about 15Gb file. But I take error: ```...
My run of "cargo run --example mnist-training" has error like: ``` Error: Api error: request error: https://huggingface.co/datasets/mnist/resolve/refs%2Fconvert%2Fparquet/mnist/test/0000.parquet: Network Error: timed out reading response ``` 1. I have a network proxy...
Hi, I'm a relatively new Rust learner and wanted to use Candle as a way of learning more about this language. I am trying to implement in Rust the [SuperPoint...
Just wondering if anyone has try to run the m2m100 model with candle, any help would be awesome thanks advance
After trying llama example with either `cuda` or `flash-attn` features, I realized the generation times are quite similar. I would expect flash attention to have a significant improvement in the...
I hope to add [PixelShuffle](https://pytorch.org/docs/stable/_modules/torch/nn/modules/pixelshuffle.html#PixelShuffle) and [PixelUnshuffle](https://pytorch.org/docs/stable/_modules/torch/nn/modules/pixelshuffle.html#PixelShuffle) in pytorch I found this layer missing when porting some super-resolution and GAN models
Use a pure rust implementation of `protox` instead of binary `protoc` `protox` has more friendly error reporting and is better integrated with the rust ecosystem.
This issue aims at keeping track of the models that would be interesting to get added to candle. Feel free to make a comment to mention a new model, or...
