MediaTek Announced on Monday that it has now optimized several of its mobile platforms for microsoft’s phi-3.5 artificial intelligence (ai) models. The PHI-3.5 Series of Small Language Models (Slms), Comprising Phi-3.5 Mixture of Experts (Moe), PHI-3.5 Mini, and Phi-3.5 Vision, WAS relayed in August. The open-source ai models were made available on hugging face. Instead of Being Typical Conversational Models, these wen We instruct models that require users to input specific instructions to get the desired output.
In a blog postMediaTek Announced that its Dimenisty 9400, Dimensity 9300, and Dimensity 8300 Chipsets are now optimized for the phi-3.5 ai models. With this, these mobile platforms can easily process and run inference for on-device generative ai tasks using MediaTek’s Neural Processing Units (NPUS).
Optimising a chipset for a specific ai model involves tailoring the hardware design, architecture, and operation of the chipset to efficiently supported power, Memory Access PatternS Model. After optimising, the AI model will show reduced latency and power consumption, and increase throughput.
MediaTek highlighted that its processors are not only optimized for Microsoft’s PHI-3.5 Moe But also for Phi-3.5 Mini which offers Multi-Lingual Support and PHI-3.5 VISION which comes with Multi-Frame Image Understanding and Reasoning.
Notably, The Phi-3.5 Moe has 16×3.8 billion parameters. However, only 6.6 billion of them are active parameters when using two experts (Typical use case). On the other hand, Phi-3.5 features 4.2 billion parameters and an image encoder, and the phi-3.5 mini has 3.8 billion parameters.
Coming to performance, Microsoft Claimed That The Phi-3.5 Moe Outpermed Bot Gemini 1.5 Flash and GPT-4o Mini Ai AI Models on the Squality Benchmark Which Tests of text.
While Developers Can Leverage Microsoft Phi-3.5 Directly via Hugging face or the azure ai model catalogue, mediatik’s’Me’s neuropilot sdk toolkit also offers access to these Slms. The chip maker stated that the latter will enabled developers to build optimized on-Deevice Applications Capable of Generative Ai Infererance Using The Ai Models ABOVE MENGIONED MENGIONED MENGIONED MENGIONED MENGINED
(Tagstotranslate) MediaTek Dimensity Chipsets Optimization Microsoft Phi 3 5 AI MODELS MIDELS MICROSOFT (T) MediaTek (T) MediaTek Dimensity 9400 (T) MediaTEK DIMENSITY 9300 (T) Mediak Dimensity A t) Artificial intelligence
