大模型微调速度提升 2 倍、显存减少 70%,单卡也能训练。
KServe
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
- 仓库
- kserve/kserve
- Stars
- ★ 6,104
- Forks
- 1,727
- 语言
- Go
- 许可证
- Apache-2.0
- 最近更新
- 2026-10-11
- 访问次数
- 0