A buffer-free MoE dispatch and combine method on Ascend hardware with pooled HBM cuts intermediate relay overhead via direct expert window access.
Fusco: High-performance distributed data shuffling via transformation-communication fusion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.DC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
FEPLB reduces token and GEMM stragglers in MoE training by 50-70% using nearly free Copy Engine communication on Hopper architecture.
citing papers explorer
-
Relay Buffer Independent Communication over Pooled HBM for Efficient MoE Inference on Ascend
A buffer-free MoE dispatch and combine method on Ascend hardware with pooled HBM cuts intermediate relay overhead via direct expert window access.
-
FEPLB: Exploiting Copy Engines for Nearly Free MoE Load Balancing in Distributed Training
FEPLB reduces token and GEMM stragglers in MoE training by 50-70% using nearly free Copy Engine communication on Hopper architecture.