DigitalOcean

DeepSeek-V4-Flash-0731 is now live on DigitalOcean Inference Engine. 🆕 https://do.co/4xwayu0 A full post-training pass pushed agentic performance past DeepSeek's own V4-Pro: Terminal Bench 2.1 up from 61.8 to 82.7, while running at just 13B active parameters. Available now via Serverless or Dedicated Inference, with managed infrastructure and predictable pricing.

Finding the right balance for AI infrastructure is tough. Hyperscalers often run out of capacity, while low-cost local data centers struggle with reliability at scale. We've added more on-demand capacity to give you the availability and stability you need to scale up, minus the complexity and enterprise bloat. Built into your existing DigitalOcean projects, Kubernetes, and networking. Fully HIPAA-eligible and SOC 2 compliant. Ready to build with us? 🛠️ https://do.co/4fMMBIY

AI Inference demand is booming. 📈 Our CEO Paddy Srinivasan shared with Kelly Evans on CNBC's The Exchange today that our AI Inference Services ARR grew ~800% year over year. Per today's Q2 earnings release, our AI Customer ARR grew 212% year over year to $234 million.

Q2 was a record quarter for us and for AI-native builders. 📈 29% YoY revenue growth 2x last year's pace = teams deploying to production faster. 🤝 AI customer ARR +200% YoY = the bet you made spinning up our inference instead of DIY is paying off. ⚡ Inference Services up ~800% YoY = usage is compounding, not only growing. 🔓 Open weight models went from ~15% to ~75% of our token traffic since launch = open models and multi-model gives you the best intelligence per dollar 🔋 +20 megawatts secured, ~155 megawatts committed = we’re ready to help you grow. If you’re fighting your existing infrastructure instead of shipping your product; that’s the exact problem we’re solving. We’ve created an integrated platform that AI-native companies depend on to build, run, and scale production AI. We can help you ship faster, with better economics, and control of your intelligence. More about our Q2 results: https://do.co/4xaVvpo

Big thanks to DigitalOcean for their awesome contributions back to the open-source community! Open-sourcing model weights is only half the battle, the other half is building open, reliable serving infrastructure that actually runs them at frontier quality. In their latest engineering deep dive on serving Moonshot AI's 2.78-trillion parameter Kimi K3 model on Day 0, the DO team showcased what real community-driven engineering looks like: 🟣 Leveraging llm-d for GPU Heterogeneity: DigitalOcean built their distributed inference stack using llm-d, taking advantage of its native support for heterogeneous GPU types. This allowed them to seamlessly onboard K3's ~1.56 TB weight footprint across both NVIDIA HGX™ B300 and AMD Instinct™ MI350X platforms without rewriting their core serving layer. 🟣 Collaborative Optimization: They worked alongside open-source maintainers like vLLM to tune the serving recipe, raising batching ceilings, fine-tuning MXFP4 quantization, and speeding up prefill paths. 🟣 Battle-Testing Open Weights: By running K3 through Moonshot's Kimi Vendor Verifier (KVV) suite, they tracked down complex edge cases in dynamic tool calling, schema-constrained decoding, and streaming spec compliance, sharing those fixes and learnings back with the broader ecosystem. Kudos to the DigitalOcean team for proving that serving massive open models on day zero is best done together. 👏 Check out the full "Under the Hood" engineering breakdown: https://lnkd.in/eYXVWavF

Great to see DigitalOcean highlight their use of llm-d to support Kimi K3 support on Day 0. From their guide (link in the comments): "We built our distributed inference stack with llm-d because it includes native support for GPU type heterogeneity. This let us quickly onboard K3 to both AMD and NVIDIA platforms." llm-d's support for multiple accelerators, like Google Cloud TPUs and GPUs from NVIDIA and AMD, make it the best choice for model & AI infrastructure providers. cc: Carlos Costa, Pete Cheslock, Robert Shaw, Abdullah Gharaibeh, Akshay Ram, Nathan Beach, Maroon Ayoub

Getting Kimi (Moonshot AI) K3, all 2.8T parameters of it, production-ready and fast on day zero is complex. We take on that complexity so you don’t have to. 🤖 https://do.co/4w4Saap That meant engineering support for K3's dynamic tools, streaming, and reasoning controls, then verifying our work against Moonshot's own test suite, not our reconstruction of it. Alongside that, we tuned the serving recipe with the vLLM team for NVIDIA HGX™ B300 and AMD Instinct™ MI350X GPUs, so the model isn't just correct, it's fast. The result: you run Kimi K3 on DigitalOcean without thinking about the serving layer at all. This is how. ⬇️

When a senior misses a daily check-in call, someone needs to know immediately. ConfirmOk builds that safety net for police departments, senior communities, and families who can't be there in person. After outages on their old platform put those calls at risk, ConfirmOk moved to DigitalOcean App Platform and Managed PostgreSQL, giving their small team reliable, event-driven infrastructure without a dedicated DevOps hire.

Incredible to see the open model momentum continue. Seeing more than 230 organizations rally around open weights reinforces what’s possible when the ecosystem comes together. Thank you to Microsoft for your partnership, and to everyone helping strengthen the open ecosystem. 🤝