RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation #295

Open

Open

RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation#295

Labels

TODO-未读area/LLMtype/paper

https://arxiv.org/pdf/2404.12457

Co-design RAG 和 LLM inference

Metadata

Assignees

No one assigned

Labels

TODO-未读area/LLMtype/paper

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests