BentoML

QwQ-32B is now supported in #OpenLLM! Try it out today: ?? Serve locally: ?????????????? ?????????? ??????:?????? ?? Deploy to #BentoCloud: ?????????????? ???????????? ??????:??????

AI Platforms - NVIDIA AI Integrated Partners Ecosystem ! Inviting to NVIDIA’s AI Platform Partner ecosystem this NVIDIA GTC We will be showcasing solutions for Data, AI, and ML workflows and discover scalable compute frameworks, optimized software stacks, and integrated platforms accelerating the development of #AgenticAI and redefining enterprise AI infrastructure. Last year, the MLOps & LLMOps Pavilion was a huge success, and I’m thrilled to continue the momentum as we introduce the "AI Platforms Pavilion" at NVIDIA GTC 2025! AI Platforms Pavilion Exhibitors of 2025: Databricks | Simplismart | AMAX |Anaconda, Inc. | BentoML | ClearML | Codeium | Canonical | Cohesity | Couchbase | Dataiku | Dataloop AI | DataRobot | Domino Data Lab | illumex | H2O.ai | JFrog | Nexla | Quali | Quantiphi | Rescale | Roboflow | Securiti | Teradata | Union.ai | VMware | Weights & Biases. Few 2024 exhibits/partners will be missed on the pavilion floor :) Run:ai (Acquired by NVIDIA) Deci AI (Acquired by NVIDIA) Brev.dev (Acquired by NVIDIA) March 17 - 21st, 2025, Mark your calendars & join us as we push the boundaries of AI Infrastructure Full Stack ! https://lnkd.in/gJAAWNJR Proud to host this with my NVIDIA colleagues, showcasing our technical collaboration and joint efforts with partners driving Enterprise AI at scale. NVIDIA MLOps Pavilion cocktail party in GTC 2024

?? The BentoML team is heading to NVIDIA GTC next week! We'll be at booth #2020 and can't wait to reconnect, share insights, and explore the latest breakthroughs in AI with all of you! If you're there and want to discuss BentoML, AI infra, ML challenges, or simply catch up, we'd love to chat! ?? Looking forward to seeing many familiar faces and meeting new ones in San Jose! #BentoML #NVIDIAGTC #AI #MachineLearning #GTC25

???DeepSeek AI: V3, R1, and distilled models — Which one is right for you? ? “Which DeepSeek model should I use?” ?? “What’s the difference between R1 and V3?” ?? “Is R1-Zero better than R1?” ?? “Do I really need a distilled model?” If you’ve asked these questions, you’re not alone. In our latest blog post, we break it all down so you can pick the best model for your needs, whether it’s general AI, deep reasoning, or lightweight inference. ?? You can deploy all of them privately & securely with BentoML for full customization and control. Read the full post: https://lnkd.in/g4GP8nTt #DeepSeek #AI #MachineLearning #LLMs #OpenSource #BentoML #BentoCloud

Exciting news in the AI world! QwQ-32B has just joined the open-source reasoning model ecosystem! With only 32B parameters, this model rivals cutting-edge models like DeepSeek-R1! You can deploy QwQ-32B with BentoML now ?? https://lnkd.in/gzvukY4Q ?? Watch our demo of QwQ-32B running inference on BentoCloud ?? #AI #MachineLearning #QwQ32B #OpenSource #BentoML #BentoCloud #LLM

?? Is your AI infrastructure strategy keeping up with industry trends? Find out in the 2024 State of AI Inference Infrastructure Survey Report! We surveyed 250+ AI practitioners and decision-makers to uncover the latest trends, challenges, and best practices shaping AI infrastructure in 2024. From model adoption and deployment patterns to multi-cloud strategies and infrastructure challenges, this report provides the insights you need to future-proof your AI infrastructure strategy. ?? Download the full report ???https://lnkd.in/gV8gk7uG #BentoML #AIInfrastructure #OpenSource #MachineLearning

?? Huge thanks to everyone who joined the #AGIBuildersMeetup in SF last week! Great talks from Cloudflare, BentoML and Isoform, and exciting demos from ManufactureAI, CodeIntegrity, and DeepModel! ?? Missed it? Watch the video here: https://lnkd.in/gUCeCrGG

???BentoML Newsletter: Future-Proofing Your AI Infrastructure Strategy

?? Today is the day! The AGI Builders Meetup SF kicks off tonight at 5:30 PM PST! Last chance to register ??

Struggling with the gap between #ML experimentation and production deployment? Our latest tutorial shows how to create seamless end-to-end ML pipelines by combining MLflow and #BentoML. You'll learn how to: ??Track experiments with #MLflow ??Save models to BentoML for unified management ??Create production-ready APIs with data validation ??Implement adaptive batching to handle concurrent requests ??Standardize deployment workflows for team collaboration Check out the full tutorial here: https://lnkd.in/g6dv8bde #AI #OpenSource #MachineLearning #MLOps