Explain how full-layer double buffering overlaps computation with communication during the prefill phase of an MoE model, and describe the rationale behind buffering full layers rather than individual experts.
0
1
Tags
Prep Sessions
Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Ch.2 Pipelining and State Caching Mechanisms - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Pipelined Loading via Full-Layer Double Buffering - 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
Agentic Workload Serving and Cross-Hardware Performance - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Related
Why can background transfer of layer begin immediately during the computation of layer when using full-layer double buffering?
If GPU memory is insufficient to allocate two full-layer buffers, the serving engine falls back to on-demand expert loading.
What action do the two full-layer buffers undergo once computation for a layer completes?
Explain how full-layer double buffering overlaps computation with communication during the prefill phase of an MoE model, and describe the rationale behind buffering full layers rather than individual experts.
Match each component of the MoE full-layer double-buffering architecture to its operational role.
Order the operational stages of pipelined full-layer double buffering during MoE prefill from initialization through layer progression.
Explain the timing constraint required for full-layer double buffering to completely hide expert weight communication, and explain why the GPU compute stream is idling at layer boundaries in this scenario.
Unified Slot Pool and Decode Seeding in Edge MoE Serving