CoLLM: A Unified Framework for Co-execution of LLMs Federated Fine-tuning and Inference

arXiv 2604.16400•187b23301c1e15f29e24caddddbcef8e514e892838066f9d86545ededb98755b
B-PASTEDoS-riskHieraSparseKV-cacheLLMPEFTagentic-servingautonomous-systemscloud-probingco-executiondistributed-trainingedge-computingfederated-learninggraph-neural-networksgraph-transformerinference-optimizationlatency-estimationmicroservicespower-managementprivacyreconnaissanceside-channelsparse-attentionspeculative-executionspot-instances

Paper metadata

arXiv ID
2604.16400
Version
Not specified by this published record
Category
Computer Science — Distributed, Parallel, and Cluster Computing (cs.DC)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_dc
Record identifier
187b23301c1e15f29e24caddddbcef8e514e892838066f9d86545ededb98755b
Enrichment time
2026-04-21T08:52:21Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

CoLLM: A Unified Framework for Co-execution of LLMs Federated Fine-tuning and Inference · Baitaphish