Metadata-Version: 2.4
Name: sam-gate
Version: 0.1.0
Summary: SAM-Gate: Semantic-Aware Memory Gate for heterogeneous KV-cache compression in transformer models
Project-URL: Repository, https://github.com/Regis3336/sam-gate
Author: Reinaldo
License: MIT
Keywords: attention,compression,kv-cache,llm,quantization,transformers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: faiss-cpu>=1.7.4
Requires-Dist: numpy>=1.24.0
Requires-Dist: psutil>=5.9.0
Requires-Dist: scipy>=1.10.0
Requires-Dist: torch>=2.1.0
Requires-Dist: transformers>=4.38.0
Provides-Extra: cuda
Requires-Dist: faiss-gpu>=1.7.4; extra == 'cuda'
Requires-Dist: flash-attn>=2.3.0; extra == 'cuda'
Provides-Extra: dev
Requires-Dist: build; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: twine; extra == 'dev'
Provides-Extra: plot
Requires-Dist: matplotlib>=3.7.0; extra == 'plot'
Requires-Dist: plotly>=5.14.0; extra == 'plot'
