Developers:✨Try Microsoft's Phi-3 Mini with the 128K context window at build.nvidia.com/microsoft/phi-… ✨

🦙🦙🦙 Optimize your Meta Llama 3 #inference with TensorRT-LLM

…and how! ✨ in only 4 steps ✨

📗➡️nvda.ws/3xRy4rS

AI at Meta

Excited to host AI at Meta Llama 3 models, powered by NVIDIA NIM microservice, on our NVIDIA API catalog. ➡️nvda.ws/3UppNnH

Run these performance optimized models from a browser or API endpoints to test your applications with superior contextual understanding, reasoning &

Experience Mixtral 8x22B and Mistral Large API endpoints, powered by NVIDIA NIM microservice, from our NVIDIA API catalog ➡️ nvda.ws/3Utljwt

These performance-optimized #generativeAI models by Mistral AI, excel in complex multilingual reasoning tasks, and more.

🦙 We’re excited to support AI at Meta Llama 3 models in NVIDIA TensorRT-LLM, accelerating and optimizing Llama 3 inference performance on our GPUs. #LLM

Get started ➡️ nvda.ws/4b57w4z

Break new ground in #speechrecognition with new Parakeet ASR models.

These state-of-the-art ASR models, developed in collaboration with Suno, transcribe spoken English with exceptional accuracy.

Get started today.

nvda.ws/44r0kOl

Happy Earth Day 💚 🌍

Master #LLM #inference optimization with our solutions architects Dmitry Mironov & Sergio Perez Perez.

➡️nvda.ws/49EbUq8

Uncover essential metrics, configurations, and best practices to elevate your AI projects in this #GTC24 session available free on NVIDIA On-Demand.

Leverage the power of Canary, a multilingual speech-to-text model that ranks at the top of the HuggingFace Open ASR Leaderboard with an average word error rate of 6.67%. #SpeechRecognition #transcription

nvda.ws/4d3PDFa

Learn about emerging apps, societal implications, and strategies for scaling generative AI tools effectively.

Watch the discussion with OpenAI COO, Brad Lightcap, and our VP Manuvir Das, in this informative #GTC24 session - now on YouTube. youtube.com/watch?v=M2s17p…

Available for the first time from NVIDIA, take this new certification in #generativeAI to validate and showcase your generative AI skills and expertise.

➡️ Learn more: nvda.ws/4aC8nKe

📢📢 Align Your Steps: Optimizing Sampling Schedules in Diffusion Models

research.nvidia.com/labs/toronto-a…

TL;DR: We introduce a method for obtaining improved sampling schedules for diffusion models, resulting in better samples at the same computation cost.

(1/5)

Learn about advances in optimization #AI and how cuOpt has evolved from a GPU-accelerated library to an AI cloud API, enabling recent advances in #LLM and linear programming.

This #GTC24 session is now available on-demand ➡️ nvda.ws/3Up8QtC

Super excited about Meta Llama 3 release – developers in essentially every industry will be able to take advantage of improved contextual understanding among other breakthroughs. Nuances matter a lot in every market. Trained on 24,000 GPUs with plans to go to 350,000 NVIDIA

Explore the most efficient strategies for deploying #LLM s with maximum efficiency by leveraging the capabilities of Triton Inference Server.

Watch the on-demand #GTC24 session ➡️ nvda.ws/3Ul5QP0

#inference #LLM

🥁 Llama3 is out 🥁
8B and 70B models available today.
8k context length.
Trained with 15 trillion tokens on a custom-built 24k GPU cluster.
Great performance on various benchmarks, with Llam3-8B doing better than Llama2-70B in some cases.
More versions are coming over the next

The Llama 3 models look fantastic! And we're proud to support them on Day 0 throughout NVIDIA's product stack: blogs.nvidia.com/blog/meta-llam…

Explore #LLM inference.

Join our upcoming webinar, where we will cover core concepts of LLM operation, demonstrate how changing the model settings affect output, and more. ➡️ nvda.ws/49B9bhe

📆 Tuesday April 23, 11a.m. Eastern.