PrototypeCommon
ByteDance-Seed/FlexPrefill
Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
- Owner
- ByteDance-Seed (organization)
- Stars
- Stars: 172
- Forks
- Forks: 11
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- researchlarge-language-modelsnatural-language-processingsparse-attention
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by ByteDance-Seed
All 31 repos by ByteDance-Seed- ByteDance-Seed/Depth-Anything-3Stars: 6,615PythonStable
- ByteDance-Seed/BagelStars: 6,206PythonStable
- ByteDance-Seed/VeOmniStars: 2,273PythonRC
- ByteDance-Seed/Seed1.5-VLStars: 1,594Jupyter NotebookBeta
- ByteDance-Seed/Triton-distributedStars: 1,577PythonBeta
- ByteDance-Seed/m3-agentStars: 1,471PythonBeta
Nearby in Python
All Python repos- wilbert-MD-PhD/medical-illustrationStars: 172PythonPrototype
- try2love/codex-mobile-bridgeStars: 172PythonPrototype
- ztt0216/MyAgentStars: 172PythonPrototype
- kevinw/pyflakesStars: 172PythonPrototype
- andrewebdev/django-videoStars: 172PythonPrototype
- P1sec/pysctpStars: 172PythonPrototype