Facebook -- TVM AWS Meetup Talkspecifics X78Structured and Unstructured Sparsity - Lots of 'free' wins from exploring sparsity in modern ML models - Can often prune models to 80%+ sparsity(with retraining) - Massive speedups combined0 码力 | 11 页 | 3.08 MB | 6 月前3- DeepSeek-V2: A Strong, Economical, and Efficient
Mixture-of-Experts Language ModelN. Shazeer. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. CoRR, abs/2101.03961, 2021. URL https://arxiv.org/ abs/2101.03961. L. Gao, S. Biderman, S. Black0 码力 | 52 页 | 1.23 MB | 1 年前3
共 2 条
- 1