Infinigence AI Open-Sources APXInf for Embodied Edge Inference on Jetson Thor
Infinigence AI open-sources APXInf with Tsinghua and SJTU: PI 0.5 FP8 on Jetson Thor drops end-to-end latency from ~278 ms to ~26 ms (~38.46 Hz), with Orin/Thor/RTX 4090 support and a domestic-chip roadmap.
情报摘要来自 RSS 摘要与来源元数据
Infinigence AI open-sources APXInf with Tsinghua and SJTU: PI 0.5 FP8 on Jetson Thor drops end-to-end latency from ~278 ms to ~26 ms (~38.46 Hz), with Orin/Thor/RTX 4090 support and a domestic-chip roadmap.
已通过内容安全与完整性检查同一事件仅保留代表性内容
为什么值得读
这条内容的质量分为 54，同一事件有 1 个独立来源。它与你关注的 平台政策 相关。
