Similar Items: AHASD: Asynchronous Heterogeneous Architecture for LLM Adaptive Drafting Speculative Decoding on Mobile Devices
- TokenStack: A Heterogeneous HBM-PIM Architecture and Runtime for Efficient LLM Inference
- NVLLM: A 3D NAND-Centric Architecture Enabling Edge on-Device LLM Inference
- VitaLLM: A Versatile and Tiny Accelerator for Mixed-Precision LLM Inference on Edge Devices
- XtraMAC: An Efficient MAC Architecture for Mixed-Precision LLM Inference on FPGA
- Sim-FA: A Simulator Frontend for Asynchronous Pipelines
- VitaLLM: A Versatile, Ultra-Compact Ternary LLM Accelerator with Dependency-Aware Scheduling