3 papers
cs.NI2026
High-speed Networking for Giga-Scale AI Factories
Sajy Khashab, Albert Gran Alcoz, Alon Gal +11
As distributed model training scales to span hundreds of thousands of GPUs, scale-out networks face unprecedented performance and efficiency demands. NVIDIA Spectrum-X Ethernet has…
cs.NI2026
Avoiding Cross-Datacenter Collective Congestion via Disaggregated Buffering
Mariano Scazzariello, Noga H. Rotman, Dima Gavrilenko +6
LLM training at the scale of tens of thousands of GPUs now spans multiple datacenters (DC), making cross-DC collectives over long-haul links unavoidable. A critical and overlooked…
cs.DC2025
OptiReduce: Resilient and Tail-Optimal AllReduce for Distributed Deep Learning in the Cloud
Ertza Warraich, Omer Shabtai, Khalid Manaa +5
We present OptiReduce, a new collective-communication system for the cloud with bounded, predictable completion times for deep-learning jobs in the presence of varying computation…