mediumNVIDIACoreWeaveNebius

MIG versus MPS: what isolation does each give you when sharing a GPU, and which would you pick for a multi-tenant inference node?

See the GPU-instance and compute-instance boundaries, budget a small slice, and distinguish memory capacity controls from bandwidth isolation.

Updated Oct 2026 · Learn how AI infrastructure works through explanations, worked examples and diagrams, then practise applying it to interview questions.

See the GPU-instance and compute-instance boundaries, budget a small slice, and distinguish memory capacity controls from bandwidth isolation.

This answer is included with a free account. Sign in to read it and save your progress.

free account · no card needed

Work through the numbers

Change the assumptions in a free calculator, then explain what the result establishes and what still needs measurement.

The concepts behind this question

Use these concept explanations to review the ideas behind this question.

Core

🗂️ Scheduling & OrchestrationSign in

MIG, MPS and Time-SlicingMIG, MPS and time-slicing share a GPU in different ways. Compare memory capacity, execution behavior and isolation before choosing a mechanism.

Advanced

🗂️ Scheduling & Orchestration🔒 Premium

Multi-Tenancy, Quotas and Fair ShareFollow three teams through GPU borrowing and reclaim. Distinguish quotas, reservations and fair sharing; see why a returning team may leave another above its nominal share, and why failures or indivisible jobs change what can be promised.

Advanced

📐 AI Systems Design🔒 Premium

Request Routing and Load Balancing for LLMsAn LLM router chooses a compatible replica, weighing queue time against reusable prompt state. Cached work helps only when the extra wait does not erase the saving.

Advanced

🗂️ Scheduling & Orchestration🔒 Premium

GPU Tenant Isolation BoundariesGPU allocation, virtual machines and network policies protect different boundaries. Trace each tenant's device, network and storage paths, then test both permitted work and forbidden access before declaring a shared GPU service isolated.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackYou are moving a model to fp4 inference on Blackwell. What breaks first, and how would you measure whether the result is acceptable?Next in this trackDesign a non-blocking network fabric for 512 H100s. How many switches, how are they wired, and where does the NVLink domain end?Next in this trackExplain GPUDirect RDMA. What does it remove from the data path, and when does it change performance?

FEDITOR'S NOTE

Identify the boundary that owns memory and bandwidth. Two compute instances in one GPU instance share memory resources; a capacity cap does not promise a bandwidth share.

DISCUSSION · 0

No comments yet — be the first to share your approach.