Efficiently Scaling and Deploying LLMs // Hanlin Tang // LLM's in Production Conference

Автор: MLOps.community

Загружено: 2023-05-19

Просмотров: 13009

Описание: // Abstract
Hanlin discusses the evolution of Large Language Models and the importance of efficient scaling and deployment. He emphasizes the benefits of a decentralized approach of many small specialized models over one giant AGI model controlled by a few companies. Hanlin explains the advantages of companies training their own custom models, such as data privacy concerns, and provides insights into when it is appropriate to build your own models and the available tooling for training and deployment.

// Bio
Hanlin is the CTO & Co-founder of MosaicML, an ML infrastructure startup that enables enterprises to easily train large-scale AI models in their secure environments. Hanlin was previously the Director of the Intel AI Lab, responsible for the research and deployment of deep learning models. He joined Intel from its acquisition of Nervana Systems. Hanlin has a Ph.D. from Harvard University and has published in leading journals and conferences such as NeurIPS, ICLR, ICML, Neuron, and PNAS.

Не удается загрузить Youtube-плеер. Проверьте блокировку Youtube в вашей сети.
Повторяем попытку...

Efficiently Scaling and Deploying LLMs // Hanlin Tang // LLM's in Production Conference

Доступные форматы для скачивания:

Скачать видео

Информация по загрузке:

Скачать аудио

Похожие видео

LLM Deployment with NLP Models // Meryem Arik // LLMs in Production Conference Lightning Talk 2

LLM Deployment with NLP Models // Meryem Arik // LLMs in Production Conference Lightning Talk 2

Exploring the Latency/Throughput & Cost Space for LLM Inference // Timothée Lacroix // CTO Mistral

Exploring the Latency/Throughput & Cost Space for LLM Inference // Timothée Lacroix // CTO Mistral

AI Hardware: Training, Inference, Devices and Model Optimization

AI Hardware: Training, Inference, Devices and Model Optimization

Fast LLM Serving with vLLM and PagedAttention

Fast LLM Serving with vLLM and PagedAttention

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

Но что такое нейронная сеть? | Глава 1. Глубокое обучение

Но что такое нейронная сеть? | Глава 1. Глубокое обучение

How banking APIs can unlock value for treasury teams

How banking APIs can unlock value for treasury teams

Production-Ready LLMs on Kubernetes: Patterns, Pitfalls, and Performa... Priya Samuel & Luke Marsden

Production-Ready LLMs on Kubernetes: Patterns, Pitfalls, and Performa... Priya Samuel & Luke Marsden

Большие языковые модели с нуля

Большие языковые модели с нуля

How to Scale LLM Applications With Continuous Batching!

How to Scale LLM Applications With Continuous Batching!

Unia Europejska upadnie? Co dalej z Europą?

Unia Europejska upadnie? Co dalej z Europą?

Fine Tuning Large Language Models with InstructLab

Fine Tuning Large Language Models with InstructLab

The Emerging Toolkit for Reliable, High-quality LLM Applications // Matei Zaharia //LLMs in Prod Con

The Emerging Toolkit for Reliable, High-quality LLM Applications // Matei Zaharia //LLMs in Prod Con

The HARD Truth About Hosting Your Own LLMs

The HARD Truth About Hosting Your Own LLMs

[1hr Talk] Intro to Large Language Models

[1hr Talk] Intro to Large Language Models

Квантование против обрезки против дистилляции: оптимизация нейронных сетей для вывода

Квантование против обрезки против дистилляции: оптимизация нейронных сетей для вывода

Full ML Design Mock by ex-Meta Staff Engineer (with feedback)

Full ML Design Mock by ex-Meta Staff Engineer (with feedback)

#3-Deployment Of Huggingface OpenSource LLM Models In AWS Sagemakers With Endpoints

#3-Deployment Of Huggingface OpenSource LLM Models In AWS Sagemakers With Endpoints

What if AI Doesn't Need Structure, It Needs Connection?

What if AI Doesn't Need Structure, It Needs Connection?

Визуализация внимания, сердце трансформера | Глава 6, Глубокое обучение

Визуализация внимания, сердце трансформера | Глава 6, Глубокое обучение