Understand this story
On November 17, 2026, NVIDIA announced the expansion of Slurm's support for quantum processors, enabling QPU vendors to provide a unified interface to all supercomputing centers through a single simple file. This expansion is based on the QRMI and QDMI interfaces, allowing supercomputing centers to connect new quantum processors into existing scheduling workflows without the need for custom solutions. Alice & Bob, IBM, IQM, Pasqal, Quantinuum, and MQSC have already adopted this approach, and Slurm 26.11 will be released later this month. NVIDIA also updated CUDA-Q, in which the TCBP-JOBS decoder is 13,000 times faster than the industry standard; Fermilab used CUDA-Q to shorten research that would originally have taken five months to three weeks.
AI-generated from public reports
Latest development · Report
Slurm 26.11 Brings QPUs into Supercomputing Scheduling via the HRES PluginDevelopments
1 confirmed developments
NVIDIA extends Slurm to support quantum processor integration
Source:NVIDIA:Newsroom
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 18
NVIDIA Developer · Generative AIFirst-party
Slurm 26.11 Brings QPUs into Supercomputing Scheduling via the HRES Plugin
Slurm 26.11 introduces the Hierarchical Resources (HRES) plugin, which models QPUs as native cluster-level schedulable resources, no longer subject to the GRES limitation of binding devices to a single node. HRES uses a Lua plugin to perform device health checks, job admission before node allocation, and resource release, with site policies stored in resources.yaml. The open source community projects QRMI and QDMI have released HRES plugins that can connect Slurm clusters to quantum computers from multiple vendors.
Nov 17
Wallstreetcn
NVIDIA Releases Rubin HPC GPU, Betting on AI Agents to Reshape Supercomputing
At SC26, NVIDIA unveiled Rubin HPC, a new-generation GPU designed specifically for scientific computing. A single GPU has more than 50,000 CUDA cores and uses seventh-generation NVLink, with launch expected in 2028. The CUDA-X libraries are being expanded in tandem: cuPhoton.xBeam cuts black hole data analysis from one month to 8 minutes, and Daviator delivers up to a 22x speedup for VASP quantum mechanics calculations. Vera CPU racks will be supplied by Dell, HPE, Lenovo and Supermicro in early 2027.
NVIDIA:NewsroomFirst-party
NVIDIA Expands Slurm Support to Bring Quantum Computing into Supercomputing
NVIDIA has expanded Slurm's support for quantum processors. QPU vendors can provide a unified interface to all supercomputing centers through a single simple file. Alice & Bob, IBM, IQM, Pasqal, Quantinuum, and MQSC have already adopted it, and Slurm 26.11 will be released later this month. The extension is based on the QRMI and QDMI interfaces, allowing supercomputing centers to connect new quantum processors to existing scheduling workflows without custom solutions. CUDA-Q has also been updated, with its TCBP-JOBS decoder being 13,000 times faster than the industry standard; Fermilab used CUDA-Q to shorten research that would originally have taken five months to three weeks.
AI Trends