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.
Astra-sim2. 0: Modeling hierarchical networks and disaggregated systems for large-model training at scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
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.