Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading Paper • 2511.14102 • Published 2 days ago • 19
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading Paper • 2511.14102 • Published 2 days ago • 19
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality Paper • 2609.33757 • Published 25 days ago • 225
A Survey on Inference Optimization Techniques for Mixture of Experts Models Paper • 2412.14219 • Published Dec 18, 2024
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference Paper • 2411.01433 • Published Nov 3, 2024 • 2
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference Paper • 2411.01433 • Published Nov 3, 2024 • 2