Learn Before
Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Learners will gain a comprehensive understanding of the systems architecture and runtime techniques required to serve frontier-scale Mixture-of-Experts (MoE) models on consumer and workstation hardware. The materials explore prefill pipelining, semantic-aware recurrent state reuse, bandwidth-adaptive hybrid CPU-GPU execution, and CUDA graph integration. Learners will develop the ability to analyze and optimize memory, interconnect, and compute trade-offs across dynamic, resource-constrained edge environments.
0
1
Tags
Prep Sessions
Related
Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor
Foundational Deep Learning Architectures: Transformers and Residual Networks @ University of Michigan - Ann Arbor
Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Overcoming Neural Network Degradation Through Residual Learning @ University of Michigan - Ann Arbor
Frontier Model Dynamics: Scaling Laws, Calibration, and Post-Training Alignment @ University of Michigan - Ann Arbor
Frontier Foundation Models, Capability Evaluation, and Just-In-Time Agent Harnesses @ University of Michigan - Ann Arbor
Engineering State-Bound Execution Runtimes for Autonomous Agents @ University of Michigan - Ann Arbor
The Aqueous Continuum: Biomolecular Solvation and Planetary Dynamics @ Honor
Long-Horizon Agent Reliability: Stateful Scaffolding and Runtime Verification @ University of Michigan - Ann Arbor
Evidence Before Action — AI Tutor Demo @ Honor
AI Agent Oversight: Scoping, Output Interrogation, and Decision Control @ Honor
AI Agent Oversight: Task Delegation, Output Auditing, and Accountability @ Honor
Supervising AI Agents: Decision Rights, Verification, and Accountability @ Honor
Engineering Deterministic Runtimes and Verification for Autonomous Agents @ University of Michigan - Ann Arbor
Making Recommendations Leaders Can Act On @ Honor
Making Recommendations Leaders Can Act On @ Honor (Iman YeckehZaare)
Runtime Verification and Failure Mitigation in Autonomous Agent Workflows @ University of Michigan - Ann Arbor
Adaptive Agent Runtimes: Architecture, Synthesis, and State Control @ University of Michigan - Ann Arbor
Autonomous Agent Control Planes: State Scaffolding and Resilient Execution @ University of Michigan - Ann Arbor
From Photons to Glucose: Bioenergetics of Light Energy Conversion @ University of Michigan - Ann Arbor
Biological Energy Transformation: From Sunlight to Chemical Storage @ University of Michigan - Ann Arbor
Beyond Status Updates: A Framework for High-Trust One-on-Ones @ University of Michigan - Ann Arbor
Dynamic Agent Scaffolding: Synthesis, Diagnostic Repair, and Evolutionary Optimization @ University of Michigan - Ann Arbor
Synthetic recommendation evaluation October 4 @ Honor
Synthetic grading retest October 4 @ Honor
Home Composting Fundamentals for Backyard Gardeners @ University of Michigan - Ann Arbor
Making Recommendations Leaders Can Act On — October 7 Demo @ Honor
Custom Pygments Lexer Engineering for Magma @ University of Michigan - Ann Arbor
Tokenizing Source Code: Classifying Keywords and Operators in Pygments @ University of Michigan - Ann Arbor
Evidence to Action: Making Defensible Workplace Decisions @ Honor
Learn After
Ch.1 Edge Serving Bottlenecks and Dynamics - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
2608.16157v1.pdf
Ch.2 Pipelining and State Caching Mechanisms - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Ch.3 Adaptive Runtime Policies and Device Execution - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Ch.4 Platform Adaptation and Performance Evaluation - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor