在 8 台 NVIDIA DGX Spark 节点上运行前沿级 AI 模型
Running Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes
NVIDIA 在 GTC Berlin 宣布，DGX Spark 支持将更多节点互联，最多可在 8 台 DGX Spark 节点上运行前沿级 AI 模型。该方案面向需要数百 GB 内存的前沿架构，支持多模型并行编排与链式推理调用。
AI developers aren’t just running a single model anymore—they’re orchestrating multiple models in parallel, chaining inference calls, and experimenting...
AI developers aren’t just running a single model anymore—they’re orchestrating multiple models in parallel, chaining inference calls, and experimenting with frontier-class architectures that demand hundreds of gigabytes of memory. NVIDIA DGX Spark was built to bring AI development to the desk, and now you’ll be able to link even more Spark nodes together. At GTC Berlin…
来源：NVIDIA Developer Blog · developer.nvidia.com