ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers

Documenti analoghi

• VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers
  di: Wang, Run, et al.
  Pubblicazione: (2025)
• VMXDOTP: A RISC-V Vector ISA Extension for Efficient Microscaling (MX) Format Acceleration
  di: Wipfli, Max, et al.
  Pubblicazione: (2026)
• Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow
  di: Wiese, Philip, et al.
  Pubblicazione: (2024)
• MXDOTP: A RISC-V ISA Extension for Enabling Microscaling (MX) Floating-Point Dot Products
  di: İslamoğlu, Gamze, et al.
  Pubblicazione: (2025)
• MiniFloat-NN and ExSdotp: An ISA Extension and a Modular Open Hardware Unit for Low-Precision Training on RISC-V cores
  di: Bertaccini, Luca, et al.
  Pubblicazione: (2022)