5 posts tagged with "Physical AI"

The integration and optimization journey between Mellerikat EVA and Rebellions NPU clearly demonstrates the future direction of next-generation AI infrastructure. Through this project, we verified that NPU-based architectures can address the high cost and power consumption challenges of traditional GPU-centric infrastructures. In particular, in Physical AI environments—where real-time perception and reasoning are critical—we confirmed the potential to achieve both significant TCO (Total Cost of Ownership) reduction and high performance simultaneously.

Today, we would like to share the porting process of moving GPU-based models to NPUs, along with the technical challenges behind it, which many people have been curious about.

1. The NPU Porting Process for GPU Models​

Since NPUs are designed to accelerate specific types of computations, newly released models cannot be executed immediately without adaptation. To fully utilize the hardware’s capabilities, several essential steps are required.

• Model Conversion

  The original models developed in PyTorch or TensorFlow must be converted into an executable format that the NPU can understand. Using the ATOM Compiler from Rebellions, the model’s computational graph is analyzed and converted into the .rbln executable format optimized for the NPU architecture.

• NPU-Optimized Compilation

  The model is compiled into a hardware-optimized executable using the compiler in the Rebellions SDK (RBLN SDK).

  • Graph Optimization: Removes redundant operations and reorganizes the data flow.
  • Operator Fusion: Combines multiple small operations into a single large kernel to reduce memory access and execution overhead.
  • Data Layout Optimization: Adjusts tensor layouts to match the NPU memory architecture, improving data access efficiency.

• Quantization

  Computational precision is adjusted to match the NPU architecture, improving both performance and memory efficiency. In the case of EVA, we optimized the model to ensure stable performance under an FP16-based inference environment.

• vLLM Integration and Validation

  The optimized model is deployed within the vLLM-RBLN serving framework. Key metrics such as TTFT (Time To First Token) and throughput are measured and validated against GPU-based environments.

2. EVA Application Optimization and Technical Challenges​

After porting the foundation model, the next step is deploying the actual service layer—the EVA Application. During this stage, we have been implementing the following optimization roadmap.

• EVA Vision Optimization (1:1 Mapping & Batching)

  We mapped NPU cores and Vision Workers in a 1:1 configuration, eliminating context-switching overhead. In addition, by applying continuous batching techniques, we are building a foundation capable of processing data from hundreds of cameras in real time without latency.

• EVA Agent Optimization (Reducing VLM Load)

  The input resolution of the Vision-Language Model (VLM) was standardized to 1280×720, and a two-stage reasoning architecture was applied to minimize unnecessary VLM calls. This immediately reduces the computational load on the Vision Encoder, which is one of the most expensive components in the pipeline.

• System Memory Management and KV Cache Optimization

  In collaboration with Rebellions, we analyzed the memory usage patterns of vLLM-RBLN instances and improved resource utilization using a page-based memory management structure. This optimization allows the system to process a larger volume of visual data reliably within the same hardware environment.

• Parallel Processing of the VLM Vision Encoder

  We are also improving the parallel execution architecture of the Vision Encoder, which accounts for a large portion of the computation in VLM inference. By optimizing how Vision Encoder operations are distributed across multiple NPU cores, we aim to significantly improve VLM serving throughput.

3. Conclusion: Evolving from PoC to a Production-Ready Solution​

We are continuously addressing technical challenges discovered during stress testing while refining optimizations that maximize hardware utilization. From parallel processing of the Vision Encoder through close collaboration with Rebellions to the development of an intelligent scheduler within the EVA platform, every step is part of transforming “EVA on NPU” from a simple proof-of-concept (PoC) into a production-ready solution.

Ultimately, the success of AI services depends on meeting three essential conditions: economic efficiency, scalability, and service quality. EVA will continue to actively adopt the latest NPU technologies and present a global standard for Physical AI platforms—delivering the most competitive TCO and outstanding performance for our customers.

When Can AI Intervene in the Real World?​

Accidents in industrial environments happen without warning. Moments such as a worker collapsing, an arm getting caught in machinery, or a fire breaking out usually occur within seconds.

Physical AI should not stop at recognizing these moments. It must be capable of translating perception into physical action on site.

In this post, we walk through a LEGO-based simulation to show how EVA detects incidents and how its decisions are connected to real equipment actions as a single, continuous flow.

Simplifying Industrial Scenarios with LEGO​

Instead of replicating complex industrial environments in full detail, we simplified accident scenarios using LEGO.

We designed independent scenarios for:

• a worker collapsing,
• an arm being caught in equipment,
• and a fire breaking out.

EVA Accelerates the Golden Time for Fire Response​

Securing the “golden time” during a fire incident in manufacturing facilities is one of the most critical factors in protecting both human life and physical assets. Traditional fire detection systems have long relied on physical sensors, but camera-based intelligent detection technologies are now rapidly replacing this role.

In this post, we analyze EVA’s smoke detection performance through a real-world validation test conducted at an LG Electronics facility and examine the technical significance of the results.

Field Validation Test: 8 Seconds vs. 38 Seconds​

A smoke detection test simulating a real fire scenario was conducted at an LG Electronics production site. The core objective of this test was to compare the detection speed between the existing smoke detectors and the newly introduced EVA system.

The results were highly encouraging. Based on the moment when smoke began to rise, the average response times of each system were as follows:

Conventional smoke detector: Smoke detected approximately 38 seconds after occurrence

As a result, EVA identified and propagated the hazardous situation more than four times faster than conventional smoke detectors. This 30-second difference represents a decisive window that can determine the success or failure of initial fire suppression.

Beyond Observation: AI That Takes Action​

The core challenge for AI today is no longer just analyzing data or describing scenes. A truly intelligent system must be able to drive meaningful actions in the physical world or corporate operational systems based on its analysis.

EVA is now moving beyond the role of 'eyes' and 'brain' that perceive visual information and judge situations, to join with the 'hands'—the Workflow Builder. This marks the completion of an End-to-End automation structure that moves past passive, notification-centric monitoring to independently judging site conditions and solving problems.

Beyond Robot AI...​

The concept of Physical AI is often equated with robotic technology. Many envision a future where robots freely navigate spaces and perform tasks on behalf of humans. However, the reality is that it will take considerable time until technology reaches that level. Despite this, much of the current discussion around Physical AI remains robot-centric — which is limiting.

Physical AI does not need to exist solely in the form of a robot. There are already a wide variety of interfaces in our physical world that can interact with AI.