most citedKernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.DCShow all

2 papers · 1 filter

cs.DC2026

MegaFlux: Skew-Resilient MoE Megakernels via Pipelined Expert Replication

Jianzhu Yao, Siva Kumar Sastry Hari, Vignesh Balaji +4

Mixture-of-experts (MoE) megakernels fuse expert-parallel communication with expert computation. However, under fixed expert placement, routing skew creates GPU stragglers: overloa…

cs.DC2026

Regulating Branch Parallelism in LLM Serving

Swapnil Gandhi, Siva Hari, William J. Dally +1

Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or und…