Linpeng Tang

Featured in: Favicon

thenewstack.io

Articles

WebAssembly, Large Language Models, and Kubernetes Matter

Apr 30, 2024 | thenewstack.io | Torsten Volk |Linpeng Tang |Jeffrey Burt |April E. Cho

WebAssembly (WASM) makes it dead simple to develop, build, run, and operate the exact same code on any piece of hardware you can find under your desk, in your data center, in your AWS account, or on the control unit of a 30-ton harvester in a corn field. While I had talked with Fermyon’s CEO Matt Butcher about this vision back at KubeCon 2022 in Detroit, today there are actual production-ready use cases that bring tangible value.
SQL Vector Databases Are Shaping the New LLM and Big Data Paradigm

Apr 29, 2024 | thenewstack.io | Linpeng Tang |Jon Udell |Oladimeji Sowole |Eric Newcomer

The rise of powerful large language models (LLMs) like GPT-4, Gemini 1.5 and Claude 3 has been a game-changer in AI and technology. With some models capable of processing over 1 million tokens, their ability to handle long contexts is truly impressive. However:Many data structures are too complex and constantly evolving for LLMs to handle effectively on their own. Managing massive, heterogeneous enterprise data within a context window is simply impractical.
How to Run a Local LLM via LocalAI, an Open Source Project

Apr 6, 2024 | thenewstack.io | David Eastman |Linpeng Tang |Jeffrey Burt |April E. Cho

Earlier this year I wrote about how to set up and run a local LLM with Ollama and Llama 2. In this article, I’ll look at an alternative option for running large language models locally. While Ollama is a private company, LocalAI is a community-maintained open source project. On the face of it, they each offer the user something slightly different. From Ollama, I effectively get a platform with an LLM to play with. However, LocalAI offers a drop-in replacement to OpenAI’s API.
No Workflow Is an Island

Oct 13, 2023 | thenewstack.io | Mark Fussell |Linpeng Tang |Jeffrey Burt |April E. Cho

Establishing business processes using workflows emerged in computing decades ago and has served as the cornerstone of business automation. Fast-forward to today, and modern applications have grown incredibly complex. They incorporate various types of computation, rely on event-driven designs, communicate with multiple services, are built to handle failures and are expected to maintain high levels of security. Amid this complexity, one element remains consistent: the role of business workflows.