Tue.Jan 30, 2024

article thumbnail

Serving Quantized LLMs on NVIDIA H100 Tensor Core GPUs

databricks

Quantization is a technique for making machine learning models smaller and faster. We quantize Llama2-70B-Chat, producing an equivalent-quality model that generates 2.2x more.

126
126
article thumbnail

It’s Not Too Late to Leverage AI, but You Must Get Started Today

Dataversity

AI’s potential enchants experts across all industries. For customer support specialists, generative AI solutions have improved productivity by up to 35%. The post It’s Not Too Late to Leverage AI, but You Must Get Started Today appeared first on DATAVERSITY.

Insiders

Sign Up for our Newsletter

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

Trending Sources

article thumbnail

Welcome to the Data Intelligence Platform: Databricks + Einblick

databricks

At Databricks, we believe that AI will change the way that enterprises interact with their data. That’s why today, we're excited to welcome t.

117
117
article thumbnail

Confluent Partner Awards 2023

Confluent

We’re celebrating excellence across the Data Streaming ecosystem. In this blog post, we announce the global and regional categories that Confluent will recognize across its 2023 Partner of the Year award winners.

92
article thumbnail

Cassandra Unleashed: How We Enhanced Cassandra Fleet’s Efficiency and Performance

DoorDash Engineering

In the realm of distributed databases, Apache Cassandra stands out as a significant player. It offers a blend of robust scalability and high availability without compromising on performance. However, Cassandra also is notorious for being hard to tune for performance and for the pitfalls that can arise during that process. The system’s expansive flexibility, while a key strength, also means that effectively harnessing its full capabilities often involves navigating a complex maze of configu

article thumbnail

Announcing the 2024 Data Streaming Startup Challenge Semifinalists

Confluent

The finalists and winner of the Data Streaming Startup Challenge will be announced at Kafka Summit London.

75
article thumbnail

Platform Engineering with Vending Machines, Contracts, and Pipelines

Wahl Network

Building a platform capable of scale means planning for scale in the first place. For me, this comes down to the formation of contracts – specifically platform and service contracts – and then using vending machines and pipelines to ensure the contracts are enforced and consistent. This post provides some thoughts on each of these constructs, how I use them, and where they fit together.

article thumbnail

NetFlow data and its fields vs packet capture

Noction

NetFlow data and packet capture serve distinct purposes in network monitoring. Packet capture, with detailed payload analysis, is effective for deep inspection but faces challenges in scalability and resource usage.