Punica: Multi-Tenant LoRA Serving - MLSys 2024 proceedings index entry
paper
Fields
id
sources/w3p-punica-mlsys24-proceedingsPublisher
MLSys / proceedings.mlsys.org
Kind
paper
Published
2023-10-27
Accessed
2026-10-04
notes
Static MLSys 2024 proceedings index (no OpenReview). Verbatim entry title 'Punica: Multi-Tenant LoRA Serving'. arXiv 2310.18547 via export.arxiv.org API (title match), published 2023-10-27. Relevant because multi-tenant LoRA serving is the other half of the serving story after base-model serving: shared prefixes plus a grouped-GEMM LoRA batch manager. Included because an SGL-era reader expects it next to PagedAttention and Orca.
Notes
Static MLSys 2024 proceedings index (no OpenReview). Verbatim entry title 'Punica: Multi-Tenant LoRA Serving'. arXiv 2310.18547 via export.arxiv.org API (title match), published 2023-10-27. Relevant because multi-tenant LoRA serving is the other half of the serving story after base-model serving: shared prefixes plus a grouped-GEMM LoRA batch manager. Included because an SGL-era reader expects it next to PagedAttention and Orca.
Cross-references
This record references no other records.