MIST is a new simulator for heterogeneous multi-stage LLM inference that combines hardware traces with analytical models to explore configuration trade-offs in hybrid CPU-accelerator systems.
Efficient memory management for large language model serving with pagedattention
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
citing papers explorer
-
MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
MIST is a new simulator for heterogeneous multi-stage LLM inference that combines hardware traces with analytical models to explore configuration trade-offs in hybrid CPU-accelerator systems.