FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters
Paper • 2510.11938 • Published
Yanying Lin
yanyinglin
·
AI & ML interests
None yet
Recent Activity
authored a paper 28 days ago
FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters authored a paper 28 days ago
FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving upvoted a paper 28 days ago
FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM ServingOrganizations
None yet
authored 2
papers 28 days ago