MMA routes host-GPU transfers over multiple available paths to deliver 4.62x higher peak bandwidth and lower latencies in LLM serving without hardware or driver changes.
Under- standing intra-node communication in hpc systems and datacenters.arXiv preprint arXiv:2502.20965, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MultiPath Memory Access: Breaking Host-GPU Bandwidth Bottlenecks in LLM Services
MMA routes host-GPU transfers over multiple available paths to deliver 4.62x higher peak bandwidth and lower latencies in LLM serving without hardware or driver changes.