Learn To be Efficient: Build Structured Sparsity in Large Language Models
–Neural Information Processing Systems
L TE reduces LLaMA2-7B inference latency by 25% at 50% sparsity.
Neural Information Processing Systems
Nov-20-2025, 02:47:37 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Finland > North Karelia
- Joensuu (0.04)
- Germany > Saarland
- Saarbrücken (0.04)
- Belgium > Brussels-Capital Region
- North America > United States
- Illinois > Champaign County
- Urbana (0.04)
- Michigan (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- Washington > King County
- Seattle (0.04)
- Illinois > Champaign County
- Asia > Middle East
- Genre:
- Research Report
- Experimental Study (0.93)
- New Finding (1.00)
- Research Report
- Industry:
- Information Technology (0.46)
- Technology: