P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats

Documenti analoghi

• Kratos: An FPGA Benchmark for Unrolled DNNs with Fine-Grained Sparsity and Mixed Precision
  di: Dai, Xilai, et al.
  Pubblicazione: (2024)
• NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
  di: Heo, Guseul, et al.
  Pubblicazione: (2024)
• BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration
  di: Chen, Yuzong, et al.
  Pubblicazione: (2024)
• The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency
  di: Geens, Robin, et al.
  Pubblicazione: (2026)
• IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System
  di: Seo, Minseok, et al.
  Pubblicazione: (2024)