MIG carves an H100 into up to seven hardware slices with their own SMs, memory and bandwidth; MPS lets processes share one SM pool through a single context. One gives fault and performance isolation at a fixed slice size; the other gives flexibility and a shared failure domain. The numbers that decide it.
Updated Sep 2026 · Grounded in real AI infrastructure interview loops and written to a senior-engineer editorial bar, with every number worked and every diagram hand-built.
MIG carves an H100 into up to seven hardware slices with their own SMs, memory and bandwidth; MPS lets processes share one SM pool through a single context. One gives fault and performance isolation at a fixed slice size; the other gives flexibility and a shared failure domain. The numbers that decide it.
Ranked by how closely each one overlaps this question's topic, so the first card is the thing to read if the answer above moved too fast.
Scored on a correct account of what each mechanism partitions (compute, memory, bandwidth, faults), the fit arithmetic for a slice, and a decision tied to tenant trust and workload shape.
No comments yet — be the first to share your approach.
