Łukasz Oleś (@lukas_oles) 's Twitter Profile
Łukasz Oleś

@lukas_oles

ID: 174735078

calendar_today04-08-2010 17:57:36

334 Tweet

101 Takipçi

190 Takip Edilen

Koyeb (@gokoyeb) 's Twitter Profile Photo

📣 Calling Docker Compose fans! You can now get your Docker Compose projects up and running quickly with Koyeb. 🐳 Read our latest tutorial to learn how to get started. 🚀 koyeb.com/tutorials/depl…

Janusz Pietruszyński (@pietruszynskij) 's Twitter Profile Photo

📈 #NewNormal –– Zanim przewiniesz dalej TwiXttera zobacz 7 minutową🧵o wszystkich faktach i mitach dotyczących inwestycji Intela w Polsce v/Janusz Pietruszyński Pay-Per-Share dzięki za #RT

📈 #NewNormal                                      
––
Zanim przewiniesz dalej TwiXttera zobacz 7 minutową🧵o wszystkich faktach i mitach dotyczących inwestycji Intela w Polsce

v/<a href="/PietruszynskiJ/">Janusz Pietruszyński</a> Pay-Per-Share dzięki za #RT
Łukasz Oleś (@lukas_oles) 's Twitter Profile Photo

At my previous job, we spent 2 years on a project that never launched. At Koyeb, my first small commit went live on day 3. Now, nearly 4 months and dozens of commits later, we're announcing the biggest feature I've helped build!

Yann Leger (@yann_eu) 's Twitter Profile Photo

🎉 Thrilled to share Serverless GPUs are available on Koyeb 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. ⬇️

🎉 Thrilled to share Serverless GPUs are available on <a href="/gokoyeb/">Koyeb</a> for all your AI needs!

We selected <a href="/nvidia/">NVIDIA</a> 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. ⬇️
Yann Leger (@yann_eu) 's Twitter Profile Photo

📣 I'm thrilled to announce our first-ever Launch Week! Starting June 17th, we, Koyeb, 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. 💥

Koyeb (@gokoyeb) 's Twitter Profile Photo

Serverless GPUs are available for all your AI inference needs! Up to 48GB of vRAM, 733 TFLOPs, and 900GB/s of memory bandwidth. Starting at $0.50/hr and billed by the second, all these instances have dedicated vCPUs that are equivalent to a hyperthread. 🔥

Serverless GPUs are available for all your AI inference needs!

Up to 48GB of vRAM, 733 TFLOPs, and 900GB/s of memory bandwidth.

Starting at $0.50/hr and billed by the second, all these instances have dedicated vCPUs that are equivalent to a hyperthread. 🔥
Yann Leger (@yann_eu) 's Twitter Profile Photo

📣 We are kicking off Koyeb's Launch Week with Autoscaling in GA 🎉 In short: 🏎️ (auto)scale fast 😴 sleep well 🏦 don’t break the bank We also added 2 new scaling criteria based on your feedback : ⏱️ P95 response time 🎯 # of concurrent connections Keep reading 🧵👇

Yann Leger (@yann_eu) 's Twitter Profile Photo

Just in time to save 💾 Day 3 of Koyeb's Launch Week, we are launching the technical preview of Volumes! 🎉 With blazing-fast NVMe SSDs, Volumes let you run high-performance stateful workloads: 🌐 Distributed databases 💾 Object storage 🔄 Queue systems A thread 🧵

Yann Leger (@yann_eu) 's Twitter Profile Photo

🔊 Turn up the volume and get ready for High IOPS NVMe storage! Volumes are now in public preview, meaning everyone can deploy volumes with high-performance and low-latency persistent SSDs! 🚀

🔊 Turn up the volume and get ready for High IOPS NVMe storage!

Volumes are now in public preview, meaning everyone can deploy volumes with high-performance and low-latency persistent SSDs! 🚀
Yann Leger (@yann_eu) 's Twitter Profile Photo

We're excited to announce Volume Snapshots: now in public preview on Koyeb's Washington DC, US, and Frankfurt regions! 📸 💾 🇺🇸 🇪🇺 Snapshots are automatically stored on a highly-available and durable remote store to prevent data loss in case of hardware failure. 🧵 👇

Yann Leger (@yann_eu) 's Twitter Profile Photo

Pivotal milestone at Koyeb: Scale-to-zero is now available in public preview! Combine it with autoscaling and enjoy the serverless experience ⬇️ Sleep and wake up automatically depending on requests, and scale out horizontally according to your scaling criteria.

Yann Leger (@yann_eu) 's Twitter Profile Photo

Today, we are thrilled to announce the world-premiere availability of Tenstorrent accelerators via Koyeb. 🎉 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

Today, we are thrilled to announce the world-premiere availability of <a href="/tenstorrent/">Tenstorrent</a> accelerators via <a href="/gokoyeb/">Koyeb</a>. 🎉

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
Łukasz Oleś (@lukas_oles) 's Twitter Profile Photo

What a small world :D 10 or maybe even 15 years ago, as a Hackerspace Silesia member, I contacted Vultr and asked them to help us host our stuff. They gave us some credits, and we hosted our things there for years. Today, with Koyeb, we’re joining forces

Yann Leger (@yann_eu) 's Twitter Profile Photo

Shout out to Neon - Serverless Postgres for releasing app.build an open-source AI agent that builds and deploys full-stack web apps 🔥 Super excited to see Koyeb deploying and running these AI-generated apps at scale with 1000s of new apps daily 🚀 🧵 👇

Shout out to <a href="/neondatabase/">Neon - Serverless Postgres</a> for releasing app.build an open-source AI agent that builds and deploys full-stack web apps 🔥

Super excited to see <a href="/gokoyeb/">Koyeb</a> deploying and running these AI-generated apps at scale with 1000s of new apps daily 🚀

🧵  👇