SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV

Documenti analoghi

• CryptoSRAM: Enabling High-Throughput Cryptography on MCUs via In-SRAM Computing
  di: Zhang, Jingyao, et al.
  Pubblicazione: (2025)
• No One-Size-Fits-All: A Workload-Driven Characterization of Bit-Parallel vs. Bit-Serial Data Layouts for Processing-using-Memory
  di: Zhang, Jingyao, et al.
  Pubblicazione: (2025)
• A Near-Cache Architectural Framework for Cryptographic Computing
  di: Zhang, Jingyao, et al.
  Pubblicazione: (2025)
• IMAGine: An In-Memory Accelerated GEMV Engine Overlay
  di: Kabir, MD Arafat, et al.
  Pubblicazione: (2024)
• Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference
  di: Geens, Robin, et al.
  Pubblicazione: (2026)