H2M2 uses an asymmetric HBM+LPDDR memory with compute on both sides and a dynamic kernel-mapping algorithm to speed up LLM generation, beating an LPDDR-only system by up to 2.94x but lagging an 8-HBM system by 1.57x.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hardware-based Heterogeneous Memory Management for Large Language Model Inference
H2M2 uses an asymmetric HBM+LPDDR memory with compute on both sides and a dynamic kernel-mapping algorithm to speed up LLM generation, beating an LPDDR-only system by up to 2.94x but lagging an 8-HBM system by 1.57x.