SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference

Documenti analoghi

• SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision
  di: Choi, Yuseon, et al.
  Pubblicazione: (2025)
• ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving
  di: Choi, Yuseon, et al.
  Pubblicazione: (2026)
• MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing
  di: Ma, Haiyue, et al.
  Pubblicazione: (2025)
• Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling
  di: Ma, Songchen, et al.
  Pubblicazione: (2026)
• MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
  di: Wang, Huizheng, et al.
  Pubblicazione: (2025)