31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding

Documenti analoghi

• APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design
  di: Tan, Yonghao, 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)
• A 28nm 0.22μJ/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentation
  di: Dong, Pingcheng, et al.
  Pubblicazione: (2025)
• Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
  di: Dong, Pingcheng, et al.
  Pubblicazione: (2024)
• LLM-FP4: 4-Bit Floating-Point Quantized Transformers
  di: Liu, Shih-yang, et al.
  Pubblicazione: (2023)