candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
https://onnx.ai/onnx/operators/onnx__Attention.html
https://onnx.ai/onnx/operators/onnx__SoftmaxCrossEntropyLoss.html
STFT and ISTFT are fundamental to audio processing, serving as core components in numerous models. Technical support for their implementation is highly sought.
```rust fn main() -> Result { let cifar = candle_datasets::vision::cifar::load()?; dbg!(&cifar.train_images); // Tensor[dims 50000, 3, 32, 32; u8] dbg!(&cifar.train_labels); // Tensor[dims 50000; u8] dbg!(cifar .train_images .flatten_all()? .to_vec1::()? .into_iter() .any(|x| x...
It seems like Mimi doesn't work on Cuda and using it via cpu requires 1 second to transcribe 80 ms of audio. Why is this the case? Thanks. It did...
Some of the examples don't run. - ~~`codegeex4_9b`~~ - ~~hangs indefinitely (Likely too slow for cpu)~~ - `colpali` - pdf seems to be read but getting `Error: i/o error: No...
When compiled with the `--features metal` flag some of the examples don't run. - `based` -> `cargo run --example based --features metal --release -- --prompt "Flying monkeys are" --which 1b-50b...
If you create a venv using uv and pip install gymnasium, the example command (`cargo run --example reinforcement-learning --features=pyo3 --package candle-examples -- pg`) will not find any of your installed...
Hi, I'm a big fan of candle so I implemented the LLMs below in my [repo](https://github.com/ITHwang/llm-serving-wasm) forked from candle: - Qwen2-Instruct models including quantized version - Qwen2.5-Instruct models including quantized...
