HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture

Documenti analoghi

• Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
  di: Zhou, Wenyong, et al.
  Pubblicazione: (2025)
• HPD: Hybrid Projection Decomposition for Robust State Space Models on Analog CIM Hardware
  di: Feng, Yuannuo, et al.
  Pubblicazione: (2025)
• Extending Straight-Through Estimation for Robust Neural Networks on Analog CIM Hardware
  di: Feng, Yuannuo, et al.
  Pubblicazione: (2025)
• A Time- and Energy-Efficient CNN with Dense Connections on Memristor-Based Chips
  di: Zhou, Wenyong, et al.
  Pubblicazione: (2025)
• PRIMAL: Processing-In-Memory Based Low-Rank Adaptation for LLM Inference Accelerator
  di: Chong, Yue Jiet, et al.
  Pubblicazione: (2026)