huggingface/candle
Minimalist ML framework for Rust
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #7 among Machine Learning repositories tracked this week, and #7 over the last 30 days; #867 of 2,794 repositories GStars tracks this week (top 31%).
The project lists 284 contributors on GitHub.
Peaked at #40 in the weekly ranking the week of Jan 25, its best in the past year.
Use Cases & Benefits
- Provides a minimalist machine learning framework in Rust focused on performance and ease of use, supporting CPU, GPU, and WASM backends.
- Enables lightweight, serverless ML inference with Rust's safety and speed, removing Python overhead and supporting multiple hardware accelerations.
- Use for deploying efficient, serverless ML models in Rust environments requiring low-latency inference without Python dependencies.
- Use for building and running state-of-the-art language and vision models with GPU acceleration and quantization support in Rust.
- Use for running ML models directly in browsers via WASM for interactive demos and lightweight client-side inference.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
Candle is a minimalist ML framework for Rust with a focus on performance (including GPU support) and ease of use. Try our online demos: whisper, LLaMA2, T5, yolo, Segment Anything.
Make sure that you have
candle-corecorrectly installed as described in Installation.Let's see how to run a simple matrix multiplication. Write the following to your
myapp/src/main.rsfile:
cargo runshould display a tensor of shapeTensor[[2, 4], f32].Having installed
candlewith Cuda support, simply define thedeviceto be on GPU:For more advanced examples, please have a look at the following section.
These online demos run entirely in your browser:
We also provide some command line based examples using state of the art models:
In order to use CUDA add
--features cudato the example command line. If you have cuDNN installed, use--features cudnnfor even more speedups.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+427 stars over 82 days across 10 snapshot days; best day +21 on Jul 28.
Forks
1.8K+133
Open issues
928+90
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| Comfy-Org/ComfyUI | 142.0K | +4.4K | 60 | 3 days ago |
| vllm-project/vllm | 95.2K | +1.3K | 75 | 4 days ago |
| pytorch/pytorch | 105.0K | +276 | 64 | 22 days ago |
| netdata/netdata | 81.1K | +0 | 75 | 12 days ago |
| huggingface/candle | 21.2K | +0 | 75 | — |
| kserve/kserve | 6.1K | +0 | 75 | 25 days ago |
| Category median | 95.2K | +276 | 75 | — |
Also by huggingface
Other repositories from this maintainer that GStars tracks
- Python167.6K stars
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- Python37.2K stars
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
- Python34.7K stars
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
- Python28.0K stars
lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
- Python22.0K stars
datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
Discover Repositories
Search across tracked repositories by name or description