PhyAI开源统一推理引擎，一个运行时跑VLA和世界模型，比官方快1.4-4.65倍，新模型当天就能接入。
PhyAI用同一套运行时统一模型评估、云强化学习、边缘GPU服务和机载部署，覆盖VLA模型与世界动作模型。通过适配器接口，发布当天就接入了MiniCPM-Robot，并在pi0、pi0.5、GR00T N1.7和MiniCPM-Robot上比官方实现提速1.40x-4.65x。在8块H20 GPU上，Cosmos3-Nano-Policy-DROID的延迟从2.46秒降至1.18秒（CFG=2, TP=4），提速2.08倍。分析显示pi0.5在批大小为1时动作专家占8.8%的FLOPs但占57.2%的延迟；批大小32时占比降至13.5%，吞吐约100样本/秒。引入的control-time Roofline区分推理受限与环境受限控制，pi0.5在四个LIBERO套件上属于环境受限，Cosmos3则推理受限。
PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud
Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Although these settings share the same checkpoint and action semantics, they often rely on separate inference programs. To unify them, we build PhyAI, a Physical AI inference engine with a single runtime that keeps architecture-specific conditioning, solver, cache, and output logic in model adapters while sharing graph execution, kernels, memory management, and parallel services. The same codebase runs vision-language-action (VLA) models and world-action models (WAMs) on single or multiple GPUs across onboard, edge, and cloud deployments. We used the adapter interface to add MiniCPM-Robot on the day of its release. PhyAI achieves 1.40x-4.65x speedups over the official implementations of pi0, pi0.5, GR00T N1.7, and MiniCPM-Robot. On Cosmos3-Nano-Policy-DROID it reduces latency from 2.46 to 1.18 s on eight H20 GPUs (CFG=2, TP=4), a 2.08x speedup. Specialized runtimes remain faster in several configurations, so our goal is one runtime with competitive latency rather than the fastest result in every case. Detailed profiles reveal why different models need different execution policies: on a Hopper-series GPU at batch size one, the pi0.5 action expert accounts for 8.8% of FLOPs but 57.2% of latency; at batch size 32 its share drops to 13.5% and throughput reaches about 100 samples/s. Cosmos3 remains generation-dominated and gains only 14.3% throughput as batch size increases from 1 to 16. We further introduce the control-time Roofline, which distinguishes inference-bound from environment-bound control; the measured pi0.5 points on four LIBERO suites are environment-bound while Cosmos3 stays inference-bound. Code and benchmarks: https://github.com/mingti-org/phyai.