Published Nov 7, 2023

E114: How OctoML Helps Developers Build with Llama 2 & Stable Diffusion

Explore how OctoML empowers developers with Llama 2 and Stable Diffusion through the lens of customer feedback and innovation, as Tianqi Chen delves into GenAI trends, the hybrid AI future, and the transformative evolution of Apache TVM.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

E163: Using Feedback Loops to Optimize LLM-Based Applications
Answers 383 questions
E93: Making Open Source Foundation Models a Reality with Lambda
Answers 383 questions
E125: Let's Help Engineering Teams Productionize AI
Answers 383 questions
E97: What Modern Application Delivery Looks Like With Loophole Labs
Answers 383 questions
E115: End-to-End AI Lifecycle Management with ClearML
Answers 383 questions
E77: Simplify Your ML Infrastructure With Aqueduct
Answers 383 questions
E108: LLM-Powered Search For Your Own Data
Answers 383 questions
E20: Building Programming Language & Infrastructure Company Dark
Answers 383 questions
E110: Building Functionality for Terraform
Answers 383 questions
E130: Orchestrating AI Workloads with Union AI
Answers 383 questions
E33: Evidently AI and Open Source Machine Learning Monitoring
Answers 383 questions
E129: The Race to Help Build Custom AI Models
Answers 383 questions
E144: How to Straddle Developers and Security Engineers
Answers 383 questions
E123: Real-time Video & Audio Infrastructure for Conversational AI
Answers 383 questions
E79: Spin Up Production-Like Dev Environments With Okteto
Answers 383 questions

Dexa/Open Source Startup Podcast

E114: How OctoML Helps Developers Build with Llama 2 & Stable Diffusion

Topics covered

Popular Clips

Embracing Uncertainty

Automating Deep Learning

Balancing Innovation and Demand

Building with TVM

TVM's Success Journey

Optimizing Model Performance

Evolving Technology Strategy

Future of AI

Customer-Centric Innovation

TVM Capabilities Explained

Evolving AI Applications

Building on TVM

Anticipating Customer Needs

Community-Driven Innovation

Episode Highlights

GenAI Trends

Customer Feedback

TVM Evolution

Related Episodes

E163: Using Feedback Loops to Optimize LLM-Based Applications

E93: Making Open Source Foundation Models a Reality with Lambda

E125: Let's Help Engineering Teams Productionize AI

E97: What Modern Application Delivery Looks Like With Loophole Labs

E115: End-to-End AI Lifecycle Management with ClearML

E77: Simplify Your ML Infrastructure With Aqueduct

E108: LLM-Powered Search For Your Own Data

E20: Building Programming Language & Infrastructure Company Dark

E110: Building Functionality for Terraform

E130: Orchestrating AI Workloads with Union AI

E33: Evidently AI and Open Source Machine Learning Monitoring

E129: The Race to Help Build Custom AI Models

E144: How to Straddle Developers and Security Engineers

E123: Real-time Video & Audio Infrastructure for Conversational AI

E79: Spin Up Production-Like Dev Environments With Okteto

E114: How OctoML Helps Developers Build with Llama 2 & Stable Diffusion

Topics covered

Popular Clips

Episode Highlights

GenAI TrendsTianqi Chen explores the latest advancements in AI models, focusing on Llama 2 and Stable Diffusion, and their transformative potential. He also discusses the future of hybrid AI execution, where local and global models collaborate to enhance efficiency and capability.

GenAI Trends

Customer Feedback

TVM EvolutionTianqi Chen, co-founder of OctoML, discusses the origins and development of Apache TVM, a groundbreaking machine learning compiler framework. He highlights the community-driven growth and technological challenges that have shaped TVM's evolution.

TVM Evolution

Related Episodes