Larry Lucerne’s Post

🤝 Our Integration With NVIDIA NIM for GPU-optimized LLM Inference in RAG As enterprises turn their attention from prototyping LLM applications to productionizing them, they often want to turn from third-party model services to self-hosted solutions. We’ve seen many folks struggle with this, and that’s why we're excited to integrate the new NVIDIA NIM inference microservices. NVIDIA NIM is a set of easy-to-use microservices designed to accelerate the deployment of generative AI across enterprises. This versatile runtime supports a broad spectrum of AI models—from open-source community models to NVIDIA AI foundation models, as well as custom AI models. Leveraging industry-standard APIs, developers can quickly build enterprise-grade AI applications with just a few lines of code. ➡ Learn more here: https://lnkd.in/gBfR-GZ7

🌟 Big news from COMPUTEX! Jensen Huang unveiled NVIDIA NIM on Hugging Face Inference Endpoints! 🌟 NVIDIA NIM promises to make deploying generative AI models easier and faster than ever before. ✨ Highlights: 🔹 One-click integration from Hugging Face Hub to Inference Endpoints 🔹 Launching with powerful models like Llama 3 8B and Llama 3 70B on AWS, GCP 🔹 Achieves up to 9000 tokens/sec for Llama 3 8B, setting new performance standards 🔹 New user-friendly interface for seamless deployment and monitoring 🔹 Comprehensive support for multi-cloud environments to enhance flexibility 🔹 Upcoming models: Mixtral 8x22B, Phi-3, Gemma, and more Excited about these advancements? We are too! Keep an eye out for more innovations from NVIDIA and Hugging Face. Learn more here: https://lnkd.in/e8ShX4Fs #NVIDIA #HuggingFace #AI #GenerativeAI #Innovation

What an exciting partnership announcement for Glean and NVIDIA! Here are some reasons our current and future customers are excited: #LLMOptionality: ✨ #NIM offers diverse LLM options for customer applications. #Flexibility: 💪 Swap LLMs easily for tailored AI experiences. #EasyIntegration: 😌 Quick NIM-Glean merge for easy, faster AI deployment. #CustomAssistants: 👨🔧 Use Glean's tech for unique AI assistants like #NVBot. #BotBuilding Support: 🤖 NVIDIA backs custom AI bot development. #EnterpriseReady: ☑ Designed for businesses with #RAG focus and BYO models. #Glean is doubling down on #GenAI freedom of choice for your enterprise!

Great news! Enterprises can unlock the value of business data with production-ready NVIDIA NIM inference microservices for retrieval-augmented generation, integrated in #Cohesity and other platforms! Get all the details. #Cohesity @Cohesity

Great news! Enterprises can unlock the value of business data with production-ready NVIDIA NIM inference microservices for retrieval-augmented generation, integrated in #Cohesity and other platforms! Get all the details. #Cohesity @Cohesity

Databricks, in partnership with NVIDIA, is pioneering the #AI revolution, enabling businesses to build custom AI models and own their intellectual property. Ali Ghodsi, CEO of Databricks, highlights on CNBC’s 'The Exchange' how this collaboration empowers enterprises with NVIDIA's GPUs, fostering innovation across various sectors. This strategic partnership underscores a future where AI technologies enhance industries like customer service and financial services, lowering cost barriers and driving significant productivity gains. https://lnkd.in/eNcm_RGY #Databricks #NVIDIA #AIInnovation #DataAnalytics #StrategicPartnership #DigitalTransformation

Unleash the potential of #generativeAI with the latest NVIDIA NeMo microservices. Experience enterprise-grade models with precise data curation, advanced customization, retrieval-augmented generation (#RAG), and accelerated performance. Learn more below, and catch up on the top generative AI sessions at #GTC24: https://lnkd.in/ggiNiuzq. Log in now to stay up to date.

Great news! Enterprises can unlock the value of business data with production-ready NVIDIA NIM inference microservices for retrieval-augmented generation, integrated in #Cohesity and other platforms! Get all the details. #Cohesity

Great news! Enterprises can unlock the value of business data with production-ready NVIDIA NIM inference microservices for retrieval-augmented generation, integrated in #Cohesity and other platforms! Get all the details. #Cohesity

YES! Thanks, Dean Takahashi, VentureBeat, for covering NVIDIA's Inference Microservices (NIMs), including those powered by partners such as Domino Data Lab. Excited to innovate jointly with NVIDIA on an #AI form factor that makes it even easier to deploy, manage, and scale models built in #DominoDataLab on #NVIDIA's infrastructure Here's the article: https://gag.gl/fxt56p #GenerativeAI #GenAI #ResponsibleAI #datascience #MachineLearning #ml #mlops #Innovation #EnterpriseAI #AIatscale