mirror of https://github.com/tracel-ai/burn.git
eb899db16c
* Add q_* ops to match float ops * Refactor q_* ops w/ dequant_op_quant macro * Comparison ops are already implemented by default to compare dequantized values * Add default arg min/max implementation and fix tch implementation * Avoid division by zero scale * Add default q_gather implementation (tch does not support on quantized tensor) * Add warning instead for tch quantize_dynamic * Call chunk backend implementation * Add QFloat check for q_ ops * Add tch q_min/max_dim_with_indices * Add q_ ops tests * Clippy fix * Remove dead code/comments * Fix quantization tests precision * Set higher tolerance for ndarray backend * Remove comment |
||
|---|---|---|
| .. | ||
| src | ||
| Cargo.toml | ||
| LICENSE-APACHE | ||
| LICENSE-MIT | ||
| README.md | ||
README.md
Burn Candle Backend
This crate provides a backend for Burn based on the Candle framework.
It is still in alpha stage, not all operations are supported. It is usable for some use cases, like for inference.
It can be used with CPU or CUDA. On macOS computations can be accelerated by using the Accelerate framework.
Feature Flags
The following features are supported:
cuda- Cuda GPU device (NVIDIA only)accelerate- Accelerate framework (macOS only)