2 papers
cs.DC2026
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
Jie Li, Chenxin Jia, Jinliang Shen +5
In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-expert counts (METRO), assumin…
astro-ph.HE2026
A high-resolution X-ray view of the ultra-fast outflow in MAXI J1810-222
C. Pinto, M. Del Santo, A. D'Aì +10
In previous work, it was reported that the Galactic black hole candidate MAXI J1810-222 exhibited a notable absorption spectral feature at around 1 keV in low-resolution X-ray spec…