Remove Architecture Remove Cache Remove Innovation
article thumbnail

Foundation Model for Personalized Recommendation

The Netflix TechBlog

Furthermore, it was difficult to transfer innovations from one model to another, given that most are independently trained despite using common data sources. At inference time, when multi-step decoding is needed, we can deploy KV caching to efficiently reuse past computations and maintain lowlatency.

Tuning 165
article thumbnail

Dynatrace accelerates business transformation with new AI observability solution

Dynatrace

Retrieval-augmented generation emerges as the standard architecture for LLM-based applications Given that LLMs can generate factually incorrect or nonsensical responses, retrieval-augmented generation (RAG) has emerged as an industry standard for building GenAI applications.

Cache 276
Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Netflix Cloud Packaging in the Terabyte Era

The Netflix TechBlog

By Xiaomei Liu , Rosanna Lee , Cyril Concolato Introduction Behind the scenes of the beloved Netflix streaming service and content, there are many technology innovations in media processing. Improved Architecture In order to address the limitations of our initial architecture, we proceeded to make some optimizations.

Cloud 242
article thumbnail

Netflix Android and iOS Studio Apps?—?now powered by Kotlin Multiplatform

The Netflix TechBlog

now powered by Kotlin Multiplatform By David Henry & Mel Yahya Over the last few years Netflix has been developing a mobile app called Prodicle to innovate in the physical production of TV shows and movies. The need for fast product delivery led us to experiment with a multiplatform architecture.

Mobile 279
article thumbnail

Dynatrace supports SnapStart for Lambda as an AWS launch partner

Dynatrace

Lambda serverless functions help developers innovate faster, scale easier, and reduce operational overhead, removing the burden of managing underlying infrastructure when updating and deploying code. The latest Amazon Lambda innovation, Lambda SnapStart, has day one support from Dynatrace. Understand and optimize your architecture.

Lambda 246
article thumbnail

Introducing Netflix’s Key-Value Data Abstraction Layer

The Netflix TechBlog

In this post, we dive deep into how Netflix’s KV abstraction works, the architectural principles guiding its design, the challenges we faced in scaling diverse use cases, and the technical innovations that have allowed us to achieve the performance and reliability required by Netflix’s global operations.

Latency 260
article thumbnail

Distance-Based ISA for Efficient Register Management

ACM Sigarch

To create a CPU core that can execute a large number of instructions in parallel, it is necessary to improve both the architecturewhich includes the overall CPU design and the instruction set architecture (ISA) designand the microarchitecture, which refers to the hardware design that optimizes instruction execution.