MLOps Community
+00:00 GMT

Collections

All Collections
Agents in Production 2024
Agents in Production 2024
25 Items
MLOps Community Podcast
Data Engineering for AI/ML
AIQCON SAN FRANCISCO 2024
Blog
MLOps IRL
AI in Production
ROUNDtable
MLOps Community Mini Summit
LLMs in Production Conference Part III

All Content

Popular topics
# LLMs
# LLM in Production
# AI
# Rungalileo.io
# Machine Learning
# MLops
# LLM
# Interview
# RAG
# Tecton.ai
# Machine learning
# Arize.com
# mckinsey.com/quantumblack
# Redis.io
# Zilliz.com
# MLOps
# Humanloop.com
# Snorkel.ai
# Redis.com
# Wallaroo.ai
All
Natan Vidra
Natan Vidra · Dec 19th, 2024
Intelligent Autonomous Multi Agent AI Systems // Natan Vidra // Agent Hour #2
//Abstract In this presentation, we will explore how intelligent autonomous multi-agent systems can augment workflows. By leveraging collaborative multi-agent AI systems, people can automate routine tasks and streamline complex processes. We will go over the architecture of building multi-agent systems, talk about how to coordinate teams of AI agents that work together, discuss how to monitor and optimize these systems to be intelligent, and showcase real-world applications that highlight their potential to enhance efficiency. //Bio Natan has experience working as a Data Scientist / Software Engineer within Deloitte's Applied Artificial Intelligence division. At Deloitte, Natan collaborated on many AI projects in the domains of Natural Language Processing, Computer Vision and Big Data Analytics. He wrote the Deloitte Prompt Engineering Guide, and led execution for Ready AI, enabling clients to practically go from zero to one on their AI journeys. . This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents. Sponsored by Arcade Ai (https://www.arcade-ai.com/)
# Autonomous
# Multi-Agent
# Agents
# AI agents in production
14:41
Samuel Colvin
Samuel Colvin · Dec 19th, 2024
//Abstract In this talk, Samuel will go into more detail on why they built PydanticAI and what problem they're aiming to solve. He'll also cover some of the future enhancements they plan for PydanticAI. //Bio Python and Rust engineer. Creator of Pydantic and Pydantic Logfire. Professional pedant. This is a bi-weekly "Agent Hour" event to continue the conversation about AI agents. Sponsored by Arcade Ai (https://www.arcade-ai.com/)
# Pydantic
# Agents
# Agent Hour
# AI agents in production
22:48
Guanhua Wang
Demetrios Brinkmann
Guanhua Wang & Demetrios Brinkmann · Dec 17th, 2024
Given the popularity of generative AI, Large Language Models (LLMs) often consume hundreds or thousands of GPUs to parallelize and accelerate the training process. Communication overhead becomes more pronounced when training LLMs at scale. To eliminate communication overhead in distributed LLM training, we propose Domino, which provides a generic scheme to hide communication behind computation. By breaking the data dependency of a single batch training into smaller independent pieces, Domino pipelines these independent pieces of training and provides a generic strategy of fine-grained communication and computation overlapping. Extensive results show that compared with Megatron-LM, Domino achieves up to 1.3x speedup for LLM training on Nvidia DGX-H100 GPUs.
# LLM
# Domino
# Microsoft
49:48
Learn to confidently deploy AI agents, explore their applications in CX and supply chains, tackle deployment challenges, and follow guidelines for efficient management.
# AI Agents
# Agents
# Weights&Biases
Aditya Naganath
Demetrios Brinkmann
Aditya Naganath & Demetrios Brinkmann · Dec 10th, 2024
LLMs have ushered in an unmistakable supercycle in the world of technology. The low-hanging use cases have largely been picked off. The next frontier will be AI coworkers who sit alongside knowledge workers, doing work side by side. At the infrastructure level, one of the most important primitives invented by man - the data center, is being fundamentally rethought in this new wave.
# LLMs
# AI
# Kleiner Perkins
55:57
Sophia Rowland
Sophia Rowland · Dec 10th, 2024
This article highlights SAS Viya as an all-in-one solution for MLOps, offering tools for version control, model registry, orchestration, monitoring, and deployment. It emphasizes features like experiment tracking, compute resource management, and responsible AI practices, aiming to simplify workflows while ensuring transparency and human oversight.
# SAS Viya
# MLOps
# SAS
Brij Mohan Singh
Travis Thompson
Ritwika Chowdhury
Brij Mohan Singh, Travis Thompson & Ritwika Chowdhury · Dec 10th, 2024
This blog underscores the need for robust governance frameworks to balance the efficiency of autonomous AI agents with their associated risks. To mitigate risks and enable safe deployment across domains, a modular and transparent approach, like the use of DDPs, is recommended.
# Governance for AI Agents
# Data Developer Platforms
# DDP
Vincent  Moens
Demetrios Brinkmann
Vincent Moens & Demetrios Brinkmann · Dec 3rd, 2024
PyTorch is widely adopted across the machine learning community for its flexibility and ease of use in applications such as computer vision and natural language processing. However, supporting reinforcement learning, decision-making, and control communities is equally crucial, as these fields drive innovation in areas like robotics, autonomous systems, and game-playing. This podcast explores the intersection of PyTorch and these fields, covering practical tips and tricks for working with PyTorch, an in-depth look at TorchRL, and discussions on debugging techniques, optimization strategies, and testing frameworks. By examining these topics, listeners will understand how to effectively use PyTorch for control systems and decision-making applications.
# PyTorch
# Control Systems and Decision Making
# Meta
55:26
Valdimar Eggertsson
Sophia Skowronski
Adam Becker
+1
Valdimar Eggertsson, Sophia Skowronski, Adam Becker & 1 more speaker · Dec 2nd, 2024
This November Reading Group conversation covers advanced retrieval techniques, strategies like iter-drag and hyper-drag for complex queries, and the impact of larger context windows on model performance. The Reading Group also examines challenges in generalizing these methods.
# Long-Context RAG
# Inference Scaling
# iter-drag and hyper-drag complex queries
49:19
Matt van Itallie
Demetrios Brinkmann
Matt van Itallie & Demetrios Brinkmann · Nov 29th, 2024
Matt Van Itallie, founder and CEO of Sema, discusses how comprehensive codebase evaluations play a crucial role in MLOps and technical due diligence. He highlights the impact of Generative AI on code transparency and explains the Generative AI Bill of Materials (GBOM), which helps identify and manage risks in AI-generated code. This talk offers practical insights for technical and non-technical audiences, showing how proper diligence can enhance value and mitigate risks in machine learning operations.
# Due Diligence
# Transparency
# Sema
57:02
Popular
How to Systematically Test and Evaluate Your LLMs Apps
Gideon Mendels & Demetrios Brinkmann