AlphaUncommon
mit-han-lab/duo-attention
[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
- Owner
- mit-han-lab (organization)
- Stars
- Stars: 545
- Forks
- Forks: 44
- Language
- Python
- License
- MIT
- Created
- 2024
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by mit-han-lab
All 53 repos by mit-han-lab- mit-han-lab/streaming-llmStars: 7,277PythonStable
- mit-han-lab/llm-awqStars: 3,662PythonRC
- mit-han-lab/efficientvitStars: 3,376PythonRC
- mit-han-lab/bevfusionStars: 3,236PythonRC
- mit-han-lab/temporal-shift-moduleStars: 2,229PythonRC
- mit-han-lab/once-for-allStars: 1,957PythonBeta
Nearby in Python
All Python repos- ArtemXTech/personal-os-skillsStars: 545PythonAlpha
- YunjueTech/Yunjue-AgentStars: 545PythonAlpha
- S-Sigdel/vimhjklStars: 545PythonAlpha
- bbangert/beakerStars: 545PythonAlpha
- emilmont/Artificial-Intelligence-and-Machine-LearningStars: 545PythonAlpha
- jazzband/django-recurrenceStars: 545PythonAlpha