通过集成太阳、计算和散热板实现减质量轨道AI推理
Reduced-Mass Orbital AI Inference via Integrated Solar, Compute, and Radiator Panels
AI总结:
本文提出一种分布式计算架构,通过整合太阳能板、散热器和计算功能,提高卫星计算效率与可靠性,实现高效AI推理。
摘要:
我们描述并分析了一种分布式计算架构,用于SSO计算卫星,该架构可提供每吨发射质量超过100千瓦的计算功率。该架构将太阳能板、散热器和计算功能整合到多个小面板中,形成大型阵列。由此产生的每面板大型蒸汽腔散热器面积可使集成电路的结温接近40°C,从而提高计算效率和可靠性。利用散热器结构支持太阳能板可能产生约500 W/kg的特定功率,优于现有传统实现的不足100 W/kg。假设所有组件均采用定制解决方案,一个包含16兆瓦计算能力、150吨卫星的卫星,其由20米×2200米的16000个面板组成的网格可容纳在单个星舰货舱中。该概念可扩展到更大卫星,具有更高的质量载荷或使用在轨组装。我们考虑面板尺寸从1到4平方米,以允许在蒸汽腔热传输与计算效率和面板间通信之间进行权衡。假设每面板1千瓦的设计,512个面板子阵列可运行具有500,000个标记上下文窗口和128个注意力块的代表性仅推理型LLM,以每会话553个标记/秒的速度运行,跨256个同时在轨会话。完整的卫星可支持31个此类子阵列,支持同时超过7900次推理。
英文摘要:
We describe and analyze a distributed compute architecture for SSO computational satellites that can potentially provide >100 kW compute power per launched metric ton (including deployment and station keeping mass). The architecture co-locates and integrates the solar cells, radiator, and compute functions into multiple small panels arranged in a large array. The resultant large vapor chamber radiator area per panel should permit ICs to operate at junction temperatures near 40*C with benefits in compute efficiency and reliability. Using the structure of the radiator to support the solar cells may also yield a specific power of about 500 W/kg compared to less than 100 for existing conventional implementations. Assuming development of custom solutions for all components, a 16 MW computation, 150 ton satellite comprising a 20 m x 2200 m grid of 16,000 panels can fit in a single Starship hold. The concept is scalable to much larger satellites with higher mass payloads or using on-orbit assembly. We consider panel sizes from 1 to 4 m2 to allow trading vapor chamber heat transport with compute efficiency and inter-panel communication. Assuming a 1 kW/panel design, 512-panel subarrays of the satellite can run a representative inference-only LLM with 500,000 token context window and 128 attention blocks, at a rate of 553 tokens/sec/session, across 256 simultaneous in-flight sessions. A full satellite could support 31 such subarrays, for >7900 inferences at a time.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。