MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices

Documenti analoghi

• HTVM: Efficient Neural Network Deployment On Heterogeneous TinyML Platforms
  di: Van Delm, Josse, et al.
  Pubblicazione: (2024)
• Accelerating Depthwise Separable Convolutions on Ultra-Low-Power Devices
  di: Daghero, Francesco, et al.
  Pubblicazione: (2024)
• Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers
  di: Daghero, Francesco, et al.
  Pubblicazione: (2025)
• Optimizing Foundation Model Inference on a Many-tiny-core Open-source RISC-V Platform
  di: Potocnik, Viviane, et al.
  Pubblicazione: (2024)
• MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs
  di: Russo, Enrico, et al.
  Pubblicazione: (2026)