Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading
Paper • 2511.14102 • Published • 19
Secenary
Secenary
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading upvoted a paper 11 months ago
Lumine: An Open Recipe for Building Generalist Agents in 3D Open WorldsOrganizations
None yet
upvoted a paper about 12 hours ago