MIGServe treats the physical layout of MIG instances as a first-class scheduling dimension through three techniques: buddy-aware partition placement, which preserves large contiguous free blocks by allocating next to existing occupied buddies; proactive pair-matching migration, which consolidates fragmented half-full b...
Jian-Wen Chen, Yun-Kai Liang, Bin Gao et al.· Proceedings of the Internati...· 0 citations
MIGServe treats the physical layout of MIG instances as a first-class scheduling dimension through three techniques: buddy-aware partition placement, which preserves large contiguous free blocks by allocating next to existing occupied buddies; proactive pair-matching migration, which consolidates fragmented half-full b...
Jian-Wen Chen, Yun-Kai Liang, Bin Gao et al.· Proceedings of the Internati...· 0 citations
KV (Key-Value) volume is introduced, a physically grounded metric that captures the spatiotemporal footprint of a request’s KV cache occupancy, and it is shown that energy per KV volume (EPV) provides a stable and reproducible signature for modeling serving energy.
Xianyi Yuan, Hanlong Liao, Kunming Zhang et al.· Asia-Pacific Workshop on Net...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
