Palantir Foundry and cuOpt drive NVIDIA supply chain allocation
NVIDIA is utilizing Palantir Foundry and cuOpt to automate its {hardware} supply chain allocation selections throughout world manufacturing websites.
The firm measures operational supply from wafer-out to first token. This window splits into time-to-rack (the transit from fab output to an assembled information centre system) and time-to-token (which covers energy, cooling, networking, and day-one software program readiness.)
Managing NVL72 and Vera Rubin part flows
Hardware scaling has magnified supply constraints. An NVIDIA Grace Blackwell NVL72 rack comprises 18 compute trays, with every tray requiring two Grace CPUs, 4 Blackwell GPUs, and 32 HBM3e reminiscence packages sourced throughout hundreds of suppliers, OEMs, and contract design companions.
The upcoming supply chain constructed for NVIDIA’s Vera Rubin structure is twice as massive because the community supporting Grace Blackwell.
Assembly can not proceed till components arrive from three designated channels: direct stock, consignment inventory, and exterior suppliers. Early shipments should wait on delayed parts, extending the metric NVIDIA phrases ‘Time of Ownership’ (the period from when a facility receives supplies to when completed sub-assemblies depart.)
Factory allocations are reworked weekly over rolling two-quarter horizons to resolve half availability, throughput limits, and buyer fulfilment schedules.
Mixed-integer linear programming through cuOpt
To coordinate these dependencies, the NVIDIA operations crew constructed the ‘Digital Supply Chain Intelligence’ command centre utilizing Palantir Foundry. Foundry’s Ontology fashions services, provider commits, part shares, and manufacturing targets as interconnected objects and hyperlinks.
NVIDIA cuOpt, an open-source library for GPU-accelerated determination optimisation, reads this operational layer instantly. Formulating distribution as a mixed-integer linear program designed to minimise TOO, the solver evaluates components constraints throughout each tier of the invoice of supplies.
Beyond outputting weekly supply schedules, cuOpt identifies energetic manufacturing unit limits, similar to regional meeting capability caps versus uncooked reminiscence availability.
Training Nemotron on qualitative operational data
Mathematical optimisation alone did not seize unstructured operational variables noticed by human planners, together with provider name transcripts, regional climate forecasts, accomplice e mail exchanges, and geopolitical occasions.
NVIDIA addressed this by post-training Nemotron 3.5 Lightning, an open-weight mixture-of-experts mannequin that includes 30 billion whole parameters and roughly three billion energetic parameters per ahead move.
The engineering pipeline processes historic data by NeMo Anonymizer to redact delicate operational fields, NeMo Data Designer to steadiness coaching examples with artificial capability disruption eventualities, and NeMo AutoModel to use low-rank adaptation (LoRA) parameters whereas maintaining base mannequin weights frozen. Palantir Autopilot manages information lineage, mannequin monitoring, and suggestion supply.
Production benchmarks and future reinforcement studying
Evaluated on historic allocation data, the post-trained Nemotron 3.5 Lightning mannequin achieved 86.7 p.c determination accuracy, in comparison with 55.5 p.c for the bigger Nemotron 3 Ultra mannequin and 17.5 p.c for the un-tuned Lightning base mannequin.
The post-trained mannequin achieved a 58.6 p.c balanced accuracy and a 57.5 p.c macro-F1 rating, outperforming Nemotron 3 Ultra’s 42 p.c balanced accuracy and 39.5 p.c macro-F1 rating.
Fine-tuning accomplished on two NVIDIA B200 GPUs inside minutes. Domain fine-tuning improved allocation selections, although manufacturing danger forecasting additional into the longer term remained tough.
Operational selections, planner revisions, overrides, and noticed manufacturing unit outputs are constantly written again to the Palantir Ontology.
NVIDIA confirmed this dataset will type choice pairs for reinforcement studying routines – scoring suggestions on allocation precision, coverage compliance, and proof grounding – with manufacturing fashions remaining strictly remoted from stay and unmonitored retraining.
See additionally: Supply chains detect fast, act slow: How AI agents fix it
Want to study extra about AI and massive information from trade leaders? Check out AI & Big Data Expo going down in Amsterdam, California, and London. The complete occasion is a part of TechEx and is co-located with different main expertise occasions together with the Cyber Security & Cloud Expo. Click here for extra data.
AI News is powered by TechForge Media. Explore different upcoming enterprise expertise occasions and webinars here.
The put up Palantir Foundry and cuOpt drive NVIDIA supply chain allocation appeared first on AI News.
