NVIDIA Alpamayo 2 Edge 边缘推理模型在车载计算与延迟限制内运行
Running AV Reasoning Models Within Onboard Compute and Latency Limits
NVIDIA Alpamayo 2 Edge 边缘推理模型可在车载计算与延迟限制内运行。该模型在 MMLU 基准上达到 70.5 分，支持 8k 上下文窗口，速度提升 3.5 倍，价格为 $3/百万 tokens，闭源部署。
Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system. Larger models provide...
Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system. Larger models provide a foundation for developing these capabilities, but moving them into a vehicle requires additional work to reduce model size, preserve useful reasoning, and validate performance on the target hardware. NVIDIA Alpamayo 2 Edge addresses…
来源: NVIDIA Technical Blog · developer.nvidia.com