Adam Y.

🤖 Learn how to build a state-of-the-art chatbot application optimized for mobile processors, using tools like the OpenVINO™ Toolkit and PyTorch with Paula Ramos, PhD during her session at #AllThingsOpen happening today at 1:45pm.

42

✨ Learn how to build and deploy custom generative models on the edge by using the early developer preview of the AI Edge Torch Generative API. Start with building a PyTorch model optimized for edge devices, and deploy with MediaPipe LLM Inference API. ➡️ https://goo.gle/4dH39Pk

132

6 Comments

Step-by-step guide to simplify deployment and boost performance for accelerated AI. ➡️ https://nvda.ws/41irg33 Whether you’re using PEFT or SFT methods for model customization, NVIDIA NIM accelerates customized model deployment for high performance inferencing in a few simple steps, using locally built, optimized TensorRT-LLM inference engines.

106

4 Comments

The explosion in the size of training and inference workloads caused by the race to larger language models has created unprecedented computational demands. The cost, availability & system architecture of GPU accelerators are slowing down the race to scaling AI workloads. Join Tobias Becker next week at TPC to explore alternative hardware/software approaches designed specifically to tackle the challenge of scaling. https://hubs.la/Q02BC2XN0

61

Model merging combines weights from multiple customized LLMs to boost resource use and enhance successful models. Introductory deep dive ➡️ https://nvda.ws/3ZmkJTB Learn how this approach: ✅ increases experimentation efficiency, and ✅ saves costs.

159

4 Comments

5 Production-Ready Open Source AI Libraries for Engineering Teams! ‣ KitOps ‣ PyTorch ‣ HuggingFace ‣ LangChain ‣ TensorFlow Read our detailed blog to learn more… (link in first comment)

3

1 Comment

Learn how you can convert a PyTorch model, trained on the web, to a mobile-optimized format. Madhur Zanwar describes the process using a few lines of code. He also discusses his journey and how one approach didn't yield satisfactory results while trying to run it in a React Native app. #machinelearning #pytorch #computervision #edgeml #reactnative #objectdetection #yolov5

14

🎬 New webinar with Arm is now live! Learn how to use PyTorch to improve performance of LLaMA family of models on AArch64. Watch here: https://hubs.la/Q02M4LNS0

75

1 Comment

In case you missed it, in celebration of Amazon S3’s 18th birthday, AWS released a number of new features for the service, including Amazon S3 Connector for PyTorch, Amazon S3 on Outposts, and Mountpoint for Amazon S3 Container Storage Interface for Bottlerocket. If you couldn’t attend, read AWS’ summary of the improvements on the AWS blog: https://hubs.li/Q02xzz4M0 #PiDay2024 #AWS #S3

2

Runhouse makes it trivial to scale your #PyTorch workloads to multi-node, multi-GPU on your own compute. You want to "go faster," not "wrestle with infra." If you bring regular PyTorch code, we'll handle the rest. In just a few lines, you can use Runhouse to launch a PyTorch Distributed-ready cluster and start running your training & inference pipelines extremely fast and very robustly. https://lnkd.in/dnB-Ttmy #ML #AI #PyTorchDistributed #DDP

12

🎯 How teams are cutting Machine Learning Engineer hiring time from 90+ days to 28 days: 1. Role-specific technical assessments that mirror real projects • Real-world problem-solving instead of whiteboard exercises • Actual code reviews from your codebase • System design challenges based on your architecture • Practical ML model optimization tasks 2. Direct access to tech leads in first interview • No HR screening delays • Technical discussion from day one • Immediate architecture alignment • Quick technical fit assessment 3. 48-hour feedback commitment from all parties • Same-day interview feedback • Next-steps within 24 hours • Offer decisions in 48 hours • Clear communication timeline 4. Streamlined technical evaluation process • One comprehensive technical round • Parallel evaluations when possible • Combined culture/technical assessments • Quick technical team consensus Teams implementing even one of these cut hiring time by 40%. "Especially effective for fast-growing startups and scale-ups" #TechHiring #MLEngineering #TechRecruitment

3

Anthropic's new methods for contextual retrieval are reshaping how we interact with documents. By parsing complex data structures and using advanced ranking mechanisms, they’re improving the quality of information retrieved. Learn more from Umair Ali Khan now. #GenAI #LLM

9

Watch this video to see how you can run a text-to-text-to-image generative AI model on a CPU with the right software stack. Join our very own Jack Ericson and Alex Sin to learn how they did it with PyTorch. Start watching here. https://intel.ly/3Uohj04 #GenerativeAI #TextToImage #PyTorch

24

Reduce costs and save valuable time during programming with the Cube Programmer’s Sequence Builder. Automate complex sequences, boost efficiency, and achieve more with fewer resources. Learn more: https://lnkd.in/gz_Mr58W What this means for you: ➡ Streamlined sequences that simplify programming processes and cut engineering time ➡ Automated code generation, including Python and XML, reducing manual efforts ➡ Enhanced accuracy by minimizing errors and ensuring compliance Ready to transform your programming workflow? Schedule a demo and see how the Sequence Builder revolutionizes efficiency and precision in your projects: https://lnkd.in/gz_Mr58W

1

It’s day 4 of our 11 Days of Inference Acceleration Techniques. Today, we’re moving on to runtime level optimization best practices. 𝐅𝐨𝐮𝐫𝐭𝐡 𝐭𝐢𝐩: 𝐓𝐚𝐤𝐞 𝐚𝐝𝐯𝐚𝐧𝐭𝐚𝐠𝐞 𝐨𝐟 𝐠𝐫𝐚𝐩𝐡 𝐜𝐨𝐦𝐩𝐢𝐥𝐚𝐭𝐢𝐨𝐧 📈 Graph compilers such as TVM, Tensor-RT, and OpenVino work by getting a computation graph of a specific model and generating an optimized code adjusted for the target hardware. Graph compilation can optimize the graph structure by merging redundant operations, performing kernel auto-tuning, enhancing memory reuse, preventing cache misses, and more. But few things to be aware of: 📝 Not all models compile equally. 📝 The impact of compilation on model performance can vary. Hence, make sure to check the architecture's ability to compile early on in the process to avoid wasting time and resources on training a model that can’t be optimized for fast inference. – What’s the #11DaysofInferenceAccelerationTechniques? The Deci team is posting, for 11 days, a series of inference acceleration techniques for deep learning applications. If you’re looking for practical tips and best practices for improving inference, follow Deci AI so you won’t miss an update. #deeplearning #machinelearning #neuralnetworks #computervision

9