Hardware Aware Transformers
[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
AI TranslationOpen Source AI & Machine LearningOpen Source
About
We release the PyTorch code and 50 pre-trained models for HAT: Hardware-Aware Transformers. Within a Transformer supernet (SuperTransformer), we efficiently search for a specialized fast model (SubTransformer) for each hardware with latency feedback. The search cost is reduced by over 10000×.
Open Source Health
- Stars
- 337
- Forks
- 50
- License
- Not stated
- Last commit
- 2 years ago
Python
Alternatives to Hardware Aware Transformers
- Localazyby LocalazyLocalazy automates translation with context-aware AI and keeps humans in control of quality.
- Lokaliseby LokaliseWorld-class AI localization platform
The Algorithmby TwitterSource code for the X Recommendation Algorithm
Recommendersby TensorFlowTensorFlow Recommenders is a library for building recommender system models using TensorFlow.- RPG_KDD2025by FacebookresearchThis repository provides the code for implementing RPG described in our KDD'25 paper "Generating Long Semantic IDs in Parallel for Recommendation".
Resources & Links
Related Categories
Using Hardware Aware Transformers?
Track its cost next to the rest of your stack and get a reminder before it renews.
Add to my stackVendor
MIT HAN Lab
Efficient AI Computing. PI: Song Han
