Leonardo Barcaroli

Today, we are thrilled to announce the world-premiere availability of @tenstorrent accelerators via @gokoyeb. 🎉 You can now access the Wormhole multi-chip solution in minutes to bring up and test frontiers of model inference performance. 🏎️ More about this strategic partnership 🧵

👩‍⚖️ ⚖️ Meet another amazing judge joining our LLM x Law Hackathon panel: Chen Gu, Legal Counsel at Dentons 🎉 Chen has firsthand experience and insight into the legal and technological challenges our participants are eager to tackle. @CodeXStanford @llama_index @neondatabase @JusMundi_com @iccwbo @MistralAI

At #DotAI2024 @yann_eu from @gokoyeb is talking about the state of AI Infrastructure. Diving into how we can optimize and increase our performance for real-time inference at the hardware and software layers.

📣 I'm thrilled to announce our first-ever Launch Week! Starting June 17th, we, @gokoyeb, will introduce new features daily to bring your deployment experience to the next level. We need your help to spread the word! Mark your calendar, follow us, and get ready to RT. 💥

At @MongoDB.local NYC? Stop at the @gokoyeb booth and say hi! Let's chat Serverless, inference, global deployments and how to use your Mongo data with some high-performance compute!

🎉 Thrilled to share Serverless GPUs are available on @gokoyeb for all your AI needs! We selected @nvidia cards with up to 48GB of vRAM, 733 TFLOPs, and 900GB/s of memory bandwidth for LLMs and genAI inference endpoints. Start for $0.50/hr, pay per second. ⬇️

Find serenity on this hilarious website of positive affirmations for SREs. srenity.online Or just use @gokoyeb for no stress ops. 🕊️ Shout out to @krazamtv for all the fun! 🙌

@gandibar I understand that this is no helpdesk, but I contacted your support 4 times and I had no reply in 11 DAYS...

🇸🇬 We're thrilled to announce the GA of our Singapore location! Deploy your apps, APIs, and AI workloads with: 🧑‍💻 Eco Instances starting at $1.61/mo 🚀 Standard Instances w/ up to 40vCPU and 128GB of RAM 🐘 Serverless Postgres Databases koyeb.com/blog/deploy-ap… Read more 🧵

@mitchellh What about @gokoyeb? 😅 koyeb.com/tutorials/depl…

I'm surprised no one has built a niche business around self-hosted GitHub Actions runners. Getting a self-hosted machine is pennies on the dollar compared to the GH pricing and I'd pay a premium to have it turnkey. Am I missing an obvious reason why this doesn't seem to exist? Basic, crude math... macOS: - 6-core macOS on an M1 is $0.16/min ($230/day @ 100% utilization) on GitHub - 8-core macOS on an M2 is $109/month (~$3.60/day @ 100% utilization) on MacStadium - Breakeven point is 681 minutes on GitHub. That isn't much! Linux: - 8-core Linux is $0.032/min ($46/day @ 100%) - 14-core dedicated server on Hetzner is currently $50/month (~$1.60/day @ 100%) - Breakeven point is ~1600 minutes on GitHub. Again, not much. 100% utilization is not unrealistic for large projects with a lot of PRs and long GHA workflows. But even if you get to a fraction of that utilization, there appears to be a huge margin you can profit from.

Looking for the fastest way to deploy the hottest stacks in town? 🔥 @gokoyeb 1-click apps let you run tools you ❤️ in seconds including @langchain  @tursodatabase @unkeydev @Quickwit_Inc @streamlit @HasuraHQ @DrizzleORM @nuxt_js and much more! koyeb.com/deploy

So, nice morning discovery. If you transfer a domain from @ArubaNetworks to another registrar, they also DELETE all the associated data of an hosting you have with them. Of course, my fault for not reading the Contract (hosting.aruba.it/domini/contrat…, 5.4). Shitty UI to say the least.

💰 We have raised $7 million in seed led by @serenavc, @JDCatISAI, @SamsungNext, @MongoDB and many more! Our mission: simplify app deployment with our global serverless platform. 🌐 Why us and what's next? ⬇️ koyeb.com/blog/we-raised…

Now this is a story all about how we built an engine designed to scale across 100 locations using @HashiCorp's Nomad and @kong's @KumaMesh, running on high-performance @equinixmetal bare metal servers. 🧑‍💻 ⚙️ 🚀 koyeb.com/blog/the-globa…

🎉 Introducing Koyeb Metrics, an easy way to monitor and troubleshoot your application performances! Say goodbye to blind troubleshooting 🤯 with our unified dashboard that tracks CPU, RAM, and HTTP requests. Here's the Metrics' story 🧵👇

One week until @InfobipShift's Conference in Zadar, Croatia! 🇭🇷 Join us at the DevEx Stage on Sept 18 at 5 p.m. for @yann_eu’s talk on what infrastructure, edge, and networking it takes to build a global serverless provider. 🌐 🚀 🎟️ Get your ticket 👉 shift.infobip.com

🚀 Want a surefire way to accelerate your Docker builds? Learn how caching works with @Docker, how to optimize your Dockerfiles for faster builds with Docker and Koyeb, and gain insights from @brmzkw's article! 🔥 koyeb.com/blog/accelerat…

You can now deploy via Dockerfile on high-performance MicroVMs across the world with @gokoyeb! 🌐 Deploy @rustlang, @ziglang, Bun from @oven_sh, @CrystalLanguage, @deno_land - anything with @Docker. 🐳 🚀 Read the announcement: koyeb.com/blog/dockerfil… Or get the news here 🧵

Lots of exciting news in this week's changelog update: 🎉 Workers are Generally Available 🚀 Seamless networking during redeploys ⚙️ Billing widget to monitor usage 🪪 API credentials for Organizations 🪵 Improved tail logs experience Read this thread to learn more🧵 ⤵️

Today, we are thrilled to announce workers are generally available in all @gokoyeb regions! 🌎 Start deploying all around the world up to 64 vCPU and 64GB of RAM per worker backed by high-end CPUs. 💪 koyeb.com/blog/deploy-an… Fun fact: Speaking of performance, in our tests, Koyeb Workers are up to 100x faster 🚀 for $1 spent than alternative solutions. Benchmarks to prove and illustrate this are coming 📈 - Stay tuned!