Congrats to the team at @resembleai on the new Chatterbox Turbo model - its a fast (sub 150ms TTFB) open-source text-to-speech model that supports paralinguistic tagging for non-speech sounds like [sigh], [giggle] and even supports voice cloning. You can check out a simple

We’d love feedback, ideas, or contributions. Open an issue or jump into the repo here: 👉

The CLI is fully backwards compatible, so nothing breaks on your side. But if you want the latest features + performance upgrades, just run: pip install --upgrade cerebrium Using Linux, Windows, or another install method? Explore all installation options in our updated Getting

What’s changed? ⚡ 23× faster CLI on average across core commands 🎨 Modern Terminal UI with Bubbletea-powered interactivity 🖥️ Cross-platform native binaries (macOS, Linux, Windows) 🤝 Open-source — contribute directly on GitHub

Sometimes its the little things that make a big impact! We’re excited to announce a complete rebuild of the Cerebrium CLI from the ground up. 🚀 We rebuilt the CLI to appeal not just to Python developers, but to developers across all frameworks and programming languages. The

The future of enterprise AI won’t just be about who trains the biggest model - it’ll be about who delivers the best performance per dollar. Our partnership with @MultiverseQC gives teams the ability to ship production workloads globally at a fraction of the cost while improving

We are always adding ways for developers to get up and running quicker with their applications. With that said, you can now use your own private Docker images as the base for your deployments. Read more in our docs here: https://t.co/XFlJKGcwXS

Claude and OpenAI are having issues due to the @Cloudflare outage. Teams running their own models aren’t seeing any disruption - self-hosted inference keeps you insulated from upstream outages. If you’re curious how to run it yourself: https://t.co/HJ0oz2w8ov"

Congrats to Replicate on the Acquisition! “Nothing will change.” - Famous last words of every acquired platform We were hoping they would change and get faster cold starts... If you want faster cold-starts, a better developer experience and some free credits - migrate now

The interface of the future is here - and it’s powered by @tavus (with a little help from us at Cerebrium). Seriously impressive! Highly recommend giving it a try https://t.co/izTTqUZ2qg 👇

🗺️ You can also explore what’s next on our public roadmap!

🧠 Have an idea for Cerebrium? You can now request features directly from your dashboard. We review every request in our weekly syncs — whether it’s a new region, framework, or integration you’d love to see. Keep building. We’re building with you. ⚡️

There are many other advantages of SGLang, and the team is constantly pushing the boundaries of inference performance - making it an excellent choice for production workloads. Happy building and tag us in applications you build!

In our example, of an Advertisement Analyzer we use SGLang to runs multiple prompts in parallel, like: “Does this ad align with the company’s description?” “Is the message clear and consistent?” “Does it target the right audience?” All prompts run concurrently, then join at the

What makes SGLang different from vLLM and TensorRT-LLM? - You can define model logic using gen(), fork(), join(), select() - no more prompt chaining - RadixAttention = smarter KV cache reuse (up to 6× faster) - No more messy JSON — FSMs guarantee clean structured output -

We just dropped a new tutorial on deploying a Vision-Language model using #SGLang - an inference framework thats used by xAI and Deepseek. We created an Advertisement analyzer taking advantage of parallel inference requests - functionality that is unique to SGLang. Checkout the

To get started: 1️⃣ Open your project’s Integrations tab 2️⃣ Click Connect GitHub and authorize 3️⃣ Select repos + deployment branch 4️⃣ (Optional) Enable auto-deploy This feature is in beta — we’d love your feedback 🫶

What it unlocks: • Continuous deployment — auto-deploy on every push • Full version control for apps/models • Branch-based deployments • Monorepo support for subdirectories

🚀 New Feature: GitHub Integration Your workflow just got simpler! Cerebrium now supports GitHub Integration — connect your repo and deploy straight from source. No YAMLs. No secrets juggling. Just push your code, and it ships ⚡️ 🎥 Demo ↓

AI teams don’t just need GPUs — they need infrastructure that moves as fast as they do. Cerebrium is redefining what serverless GPU compute means for real-time AI. ⚡️