DigitalOcean

@digitalocean

The AI-Native Cloud. ☁️ Status: @DOstatus Support: do.co/contact

do.co/twitterbio

Joined January 2012

Affiliates Replies Articles Media

DigitalOcean
@digitalocean
Aug 15
We’re closing out Ray Summit + the vLLM Conference with our happy hour, hosted with @nvidia & @inferact. 🍻 Lightning talks, live demos, cold drinks, and a room full of builders who are optimizing intelligence per dollar. RSVP today. 🎟️ do.co/4g0oAhE
DigitalOcean
@digitalocean
Aug 14
Most people wait months for the latest GPUs, like @AMD Instinct™ MI350 or 355s. We spun one up, installed @vllm_project and @Alibaba_Qwen 2.5-72B, and had it explain quantum physics in detail. Total time: under 2 minutes. ⚡️ Spot GPU Droplets are now in Public Preview.
00:00
DigitalOcean
@digitalocean
Aug 13
.@amit's repo-lens takes @Alibaba_Qwen 3.8's full context window and turns it into an honest, cited read of what a dependency actually does. Built on Serverless Inference. 🛠️
Amit Jotwani
@amit
Aug 13
Alibaba dropped Qwen 3.8 last week, and it's now on @digitalocean Serverless Inference. The thing that got my attention is the context window, hundreds of thousands of tokens in one pass. Basically a whole codebase. So I threw an entire repo at it.
00:00
DigitalOcean
@digitalocean
Aug 12
Now available: @Alibaba_Qwen 3.8-2.4T-A95B from @alibaba_cloud on DigitalOcean Serverless Inference via NVIDIA HGX™ B300 GPUs. 🤖 1M context, built for long-horizon coding. 🔗 do.co/45VBAyZ One API, usage-based pricing, no infra to manage.
00:00
DigitalOcean
@digitalocean
Aug 11
Latest-gen GPUs, without long term commitments. ☁️ Spot GPU Droplets are now in Public Preview on DigitalOcean. •NVIDIA HGX™ B300, AMD Instinct™ MI355X and MI350X, available now •Built for fault-tolerant work: batch training, batch inference, rendering •Same platform as