ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts

Documenti analoghi

• Pushing the Envelope of LLM Inference on AI-PC and Intel GPUs
  di: Georganas, Evangelos, et al.
  Pubblicazione: (2025)
• LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  di: Yang, Penghui, et al.
  Pubblicazione: (2025)
• Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures
  di: Georganas, Evangelos, et al.
  Pubblicazione: (2023)
• HiSpec: Hierarchical Speculative Decoding for LLMs
  di: Kumar, Avinash, et al.
  Pubblicazione: (2025)
• SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
  di: Sun, Ryan, et al.
  Pubblicazione: (2024)