huggingface/optimum
๐ Accelerate inference and training of ๐ค Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
- Stars
- 3.5k
- Forks
- 711
- Open issues
- 261
- Last push
- 3d ago
About optimum
optimum is a free, open-source AI inference tool by huggingface, written mainly in Python. ๐ Accelerate inference and training of ๐ค Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools. It has 3.5k GitHub stars and 711 forks, and was last updated 3d ago. It's released under the Apache-2.0 license, a standard open-source license.
- License
- Apache-2.0
- Language
- Python
- Stars
- 3,508
- Last update
- 3d ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Yes
Similar free tools
DeepSpeed43k stars ยท DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
vllm95k stars ยท A high-throughput and memory-efficient inference and serving engine for LLMs
pytorch105k stars ยท Tensors and Dynamic neural networks in Python with strong GPU acceleration
ort2.6k stars ยท Fast ML inference & training for ONNX models in Rust
BentoML8.9k stars ยท The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
pytorch-lightning31k stars ยท Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
optimum FAQ
Is optimum free?
Yes. optimum is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does optimum run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does optimum need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is optimum still maintained?
Yes. It was last updated 3d ago and has 261 open issues on GitHub.
What are alternatives to optimum?
Similar free, open-source tools include DeepSpeed, vllm, pytorch, ort.