From a "simple" finetuning to your own Mixture of Expert model using opensource models. Nowadays training from scratch an LLM is a so huge effort also for very big company. Starting from pre-trained models to create your own model is no more a way for resourceless companies, but a often a must starting point.
- Lora - Quantization and QLora - Injecting embeddings model into Lora to manage multiple Lora adapters. - Mixing models - Creating your MoE (Mixture of experts) model using several finetuned (Your own) models
Winner of three AI awards, I’ve been working in AI and machine learning for 25 years, designing and developing AI and computer graphic algorithms.I’m very passionate about AI, focusing on Audio, Image and Natural Language Processing, and predictive analysis as well.I received... Read More →
Anil Inamdar, Instaclustr by NetApp, Head of Data Solutions
For dev teams building and training their own AI models, ending up with AI solutions plagued by hallucinations and reliability issues is a (rightfully) huge concern. The good news: vector databases make generative AI considerably more reliable and less prone to hallucinations. The even better news: a number of *100% free and open source* vector databases are especially great options for supporting AI workloads.
The good news keeps coming for teams considering an open source vector database path: it isn’t necessary to invest in implementing new or exotic or proprietary or specialized data-layer solutions to harness vector databases. Many enterprises will find that their existing infrastructure can already support AI workloads (while continuing to provide the familiar data availability, scalability, and performance they already know they can trust). In particular, PostgreSQL (with the pgvector extension), OpenSearch, and Apache Cassandra 5.0 (with its new native vector indexing) are three completely open source technologies—no proprietary or open core solutions needed—that tick all the boxes for meeting enterprises’ AI workloads requirements.
Attendees of this Dev Innovation Summit session will learn how open source vector databases utilize vector embeddings to enable more accurate LLMs, and how to strategically approach and implement retrieval augmented generation (RAG) processes. Attendees will also come away with a clear understanding of the advantages offered by PostgreSQL with pgvector, OpenSearch and Cassandra 5.0 as particularly mature open source vector database strategies ready to jumpstart your organization’s competitive AI capabilities.
Anil Inamdar is the VP & Head of Data Solutions at Instaclustr by NetApp. Anil has 20+ years of experience in data and analytics roles. Joining Instaclustr in 2019, he works with organizations to drive successful data-centric digital transformations via the right cultural, operational... Read More →
Discover Intuit's in-house built developer portal journey which serves 5000+ developers and another 4000+ non developer personas - A shift from Developer Portal to Development Portal.
Intuit serves 100M users annually using a centralized Development Portal. It supports Day 0, 1 and 2 actions right out-of-the-box: from no-code infrastructure provisioning templates to monitoring dashboards and end-of-life management. But that's just where the fun starts: Intuit has a come a long way from building experiences for service developers to supporting various personas such as web, mobile, data developers as well as product managers and leaders. In this session, we will share some of our most powerful and efficient workflows (intelligent infrastructure provisioning, automated software lifecycle grading, application discovery and much more) and finally how we work with internal platform teams to add new capabilities in our Portal and its Information Architecture.
Obsolescence in tech is inevitable, making code migrations a necessary part of staying competitive. Yet, despite their potential benefits, the high costs often make these migrations unfeasible, leading businesses to delay them until they become critical for survival. But what if migrations could deliver 10x the ROI and serve as a strategic advantage instead of an unavoidable cost? In this talk, tailored for tech leaders, engineers, and business stakeholders, you’ll discover how tech giants like Meta break down and solve the challenges of code migration with effective tools and expertise—allowing them to innovate rapidly, even with very large and growing codebases. You’ll learn how to turn migrations into a powerful advantage for your team, too.
Alex, a PhD dropout in Systems Engineering, has built AI-powered automation platforms at Meta, processing billions of content daily. Alex founded Codemod to create a better version of the internal code automation platform at Meta for the rest of the world.
Ankit Jain, Aviator Technologies, Co-founder & CEO
In this talk we will delve into the nuanced world of software engineering, where the emphasis on metrics can often overshadow the crucial aspect of developer experience. We will explore how an over-reliance on metrics can hinder innovation, cause unexpected behaviors, and ultimately erode team morale.
Discover alternative approaches to scaling developer experience that prioritize human-centric methodologies over mere data points. We will also dive into practical strategies to use automation and ownership to scale developer experience.
Ankit is a cofounder and CEO of dev-productivity startup Aviator Technologies and also leads the ex-Google alumni network (Xoogler.co). Previously he led engineering teams at Sunshine, Homejoy and Shippo. Prior to that, Ankit was also an EIR at Unshackled Ventures and an engineer... Read More →
What would you envision your futuristic web framework to be like? What kind of properties would it have, and what would it enable for you?
For me, the future of web frameworks should be performant by default, developer friendly, minimal but flexible to business needs, and use both the client and the server runtimes to their maximum potential.
It’s a tough criteria, and most frameworks fail to meet a lot of these requirements. However, Solid Start is a relatively new framework that checks all of these boxes, aims for a very high ceiling, and has already inspired many popular frameworks to add similar features.
Let’s take a look at the shape of frameworks to come in this session by building a sample application with Solid Start, witness its incredible UX and DX capabilities, and how it compares to other frameworks like Next.js and Astro.
Dev Agrawal is a software engineer at Smart Data, and makes content on YouTube and Twitch around software development and design. Dev has been writing fullstack javascript applications for 7 years, has an interest in devtools that enable productivity, home brewing coffee, and heavy... Read More →
Developing cross-platform applications is complex. Some frameworks allow us to share the business logic and some go further and allow us to share the UI layer. But even then – working with device hardware requires developers familiar with each target platform to maintain it and can still lead to error-prone platform-specific code.
What if you could write it all in either C# or XAML, from any dev environment, deploy to any platform, at 5x the speed, and have it all pixel-perfect without any lock-in? Enter Uno Platform, an open-source project enabling amazing dev productivity for building Windows, Android, iOS, macOS, Linux, and WebAssembly apps!
In this session, we will provide a brief overview of what Uno Platform is and how it works before we take a deep dive under the hood and see where the magic happens.
Steve is a Senior Engineer, a .NET Microsoft MVP, and one of the core maintainers of the open-source Uno Platform project. When not at his computer, he is either watching the Montreal Canadiens lose or asleep on the couch.
Roundtables give attendees the opportunity to meet in small groups with API World, CloudX + Dev Innovation Summit speakers and industry leaders to discuss real-world topics relevant to you. These open roundtables are working sessions for in-depth industry conversations.
Dev Agrawal is a software engineer at Smart Data, and makes content on YouTube and Twitch around software development and design. Dev has been writing fullstack javascript applications for 7 years, has an interest in devtools that enable productivity, home brewing coffee, and heavy... Read More →
