EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs
cs.DC, cs.AR, cs.LG
Submitted: 2026-09-06
Updated: 2026-09-06
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Related papers
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- SAMM: Sharded Automated Market Maker
- InferScale: GPU-Native KV Injection for Personalized LLM Serving
- Vigil: Accountable Liveness against Selective Silence
- Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
- Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing