PrototypeCommon
mit-han-lab/spatten
[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
- Owner
- mit-han-lab (organization)
- Stars
- Stars: 142
- Forks
- Forks: 11
- Language
- Scala
- License
- MIT
- Created
- 2023
- Topics
- attentionhardware-accelerationllm-inferencertlspinalhdl
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by mit-han-lab
All 53 repos by mit-han-lab- mit-han-lab/streaming-llmStars: 7,275PythonStable
- mit-han-lab/llm-awqStars: 3,661PythonRC
- mit-han-lab/efficientvitStars: 3,374PythonRC
- mit-han-lab/bevfusionStars: 3,235PythonRC
- mit-han-lab/temporal-shift-moduleStars: 2,229PythonRC
- mit-han-lab/once-for-allStars: 1,957PythonBeta
Nearby in Scala
All Scala repos- leanovate/play-mockwsStars: 142ScalaPrototype
- codacy/codacy-coverage-reporterStars: 142ScalaPrototype
- stripe/bonsaiStars: 142ScalaPrototype
- scalaj/scalaj-collectionStars: 142ScalaPrototype
- backchatio/hookupStars: 142ScalaPrototype