Compiler-Assisted Speculative Sampling for Accelerated LLM Inference on Heterogeneous Edge Devices

Documenti analoghi

• Leveraging Stochastic Depth Training for Adaptive Inference
  di: Korol, Guilherme, et al.
  Pubblicazione: (2025)
• Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs
  di: de Lima, João Paulo Cardoso, et al.
  Pubblicazione: (2025)
• Full-Stack Optimization for CAM-Only DNN Inference
  di: de Lima, João Paulo C., et al.
  Pubblicazione: (2024)
• Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding
  di: Zhu, Bingjie, et al.
  Pubblicazione: (2025)
• Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
  di: Timor, Nadav, et al.
  Pubblicazione: (2025)