PrototypeCommon
thu-nics/MoA
[CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
- Owner
- thu-nics (organization)
- Stars
- Stars: 163
- Forks
- Forks: 9
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- large-language-modelsmodel-compressionsparse-attention
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by thu-nics
All 10 repos by thu-nics- thu-nics/C2CStars: 767PythonBeta
- thu-nics/awesome_ai4edaStars: 297Alpha
- thu-nics/MNSIM-2.0Stars: 219PythonPrototype
- thu-nics/DiTFastAttnStars: 192Jupyter NotebookPrototype
- thu-nics/ViDiT-QStars: 170PythonPrototype
- thu-nics/AKVStars: 170PythonPrototype
Nearby in Python
All Python repos- sherlyryn/make-tape-collageStars: 163PythonPrototype
- amathislab/terraStars: 163PythonPrototype
- weike-zhang/architecture-canvasStars: 163PythonPrototype
- josephwilk/semanticpyStars: 163PythonPrototype
- jimfunk/django-postgresql-netfieldsStars: 163PythonPrototype
- hydralabs/pyamfStars: 163PythonPrototype