Fan Wu

Chengfei Lv, Chaoyue Niu, Renjie Gu et al.

To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration. Specifically, the compute container is based on Mobile Neural Network (MNN), a tensor compute engine along with the data processing and model execution libraries, which are exposed through a refined Python thread-level virtual machine (VM) to support diverse ML tasks and concurrent task execution. The core of MNN is the novel mechanisms of operator decomposition and semi-auto search, sharply reducing the workload in manually optimizing hundreds of operators for tens of hardware backends and further quickly identifying the best backend with runtime optimization for a computation graph. The data pipeline introduces an on-device stream processing framework to enable processing user behavior data at source. The deployment platform releases ML tasks with an efficient push-then-pull method and supports multi-granularity deployment policies. We evaluate Walle in practical e-commerce application scenarios to demonstrate its effectiveness, efficiency, and scalability. Extensive micro-benchmarks also highlight the superior performance of MNN and the Python thread-level VM. Walle has been in large-scale production use in Alibaba, while MNN has been open source with a broad impact in the community.

Yanlong Peng, Zhigang Wang, Yisheng Zhang et al.

The efficient disassembly of end-of-life electric vehicle batteries(EOL-EVBs) is crucial for green manufacturing and sustainable development. The current pre-programmed disassembly conducted by the Autonomous Mobile Manipulator Robot(AMMR) struggles to meet the disassembly requirements in dynamic environments, complex scenarios, and unstructured processes. In this paper, we propose a Battery Disassembly AMMR(BEAM-1) system based on NeuralSymbolic AI. It detects the environmental state by leveraging a combination of multi-sensors and neural predicates and then translates this information into a quasi-symbolic space. In real-time, it identifies the optimal sequence of action primitives through LLM-heuristic tree search, ensuring high-precision execution of these primitives. Additionally, it employs positional speculative sampling using intuitive networks and achieves the disassembly of various bolt types with a meticulously designed end-effector. Importantly, BEAM-1 is a continuously learning embodied intelligence system capable of subjective reasoning like a human, and possessing intuition. A large number of real scene experiments have proved that it can autonomously perceive, decide, and execute to complete the continuous disassembly of bolts in multiple, multi-category, and complex situations, with a success rate of 98.78%. This research attempts to use NeuroSymbolic AI to give robots real autonomous reasoning, planning, and learning capabilities. BEAM-1 realizes the revolution of battery disassembly. Its framework can be easily ported to any robotic system to realize different application scenarios, which provides a ground-breaking idea for the design and implementation of future embodied intelligent robotic systems.

Junyi Chen, Chuheng Du, Renyuan Liu et al.

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation (i.e.,required time-between-tokens). Standard LLM serving systems suffer from the inflexibility caused by non-preemptive request scheduling and reactive memory management, leading to poor resource utilization and low request processing parallelism under request bursts. Therefore, we present TokenFlow, a novel LLM serving system with enhanced text streaming performance via preemptive request scheduling and proactive key-value (KV) cache management. TokenFlow dynamically prioritizes requests based on real-time token buffer occupancy and token consumption rate, while actively transferring KV cache between GPU and CPU memory in the background and overlapping I/O with computation to minimize request preemption overhead. Extensive experiments on Llama3-8B and Qwen2.5-32B across multiple GPUs (RTX 4090, A6000, H200) demonstrate that TokenFlow achieves up to 82.5% higher effective throughput (accounting for actual user consumption) while reducing P99 TTFT by up to 80.2%, without degrading overall token throughput.