ESC

Type to search articles...

No articles found.

↑ ↓ Navigate ↵ Open
Esc Close
Blog Tags GitHub
All tags

gpu-sharing

1 post tagged with "gpu-sharing"

June 29, 2026

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

Prism 通过 GPU 内存气球技术实现多 LLM 共享服务,统一时间共享和空间共享,SLO 达标率下支持 2.3-3.5x 更多请求,已在 10K+ GPU 生产环境部署

llm-serving inference-serving gpu-sharing memory-management multi-model-serving

Navigation

  • Work

Resources

  • Lexington Themes.

Socials

  • @Mike_Andreuzza
© 2025 MicroStudio. All rights reserved.

MicroStudio is not affiliated with Stripe, Breeew, Astro, or Tailwind Labs, nor is it endorsed or sponsored by them.