Intro The moment your app calls more than one model provider, the plumbing gets ugly. Different SDKs, different auth, no shared view of spend, and when one provider has a bad afternoon your bot just goes dark. The fix is an LLM gateway: one endpoint in front of every provider that handles routing, fallbacks, cost …
Read more “LLM Routing Solutions: Open Source vs Commercial”
Intro Conference demos always run out of clock, you show one or two outputs and the rest stay on the cutting-room floor. That’s what happened at my last Conf42 talk, How vLLM-Omni Unifies Multimodal Inference, so to make up for it I promised to share the whole code and demo videos in a proper blog. …
Read more “vLLM-Omni on Nebius H100: Serving Z-Image, Wan2.2, Qwen3-TTS & NVIDIA Cosmos 3”
Intro In the last CoreWeave post we ran vLLM on a single GPU box with mid-sized models (70-125B). DeepSeek-V3.2, on the other hand, doesn’t fit on one box (685B parameters, ~643GB even compressed). But how do you shard a whale this big across nodes and still serve it fast, at low latency, without it falling …
Read more “vLLM DeepSeek๐ Multinode Deployment on CoreWeave (KubeRay + Terraform)”
Intro When scaling AI models like DeepSeek or Qwen on Amazon EKS, engineering teams obsess over GPU utilization while quietly bleeding money on storage bloat. Because standard EBS volumes force a 1:1 replica-to-disk ratio, scaling a single 70GB model to 20 pods doesn’t cost 70GB, it forces you to provision 1.4 Terabytes of redundant EBS …
Read more “vLLM on EKS: Cut LLM Storage Costs by 95% with S3 Mountpoint”
Intro If you’ve been following along, we’ve already covered vLLM-Omni and how diffusion models work. But here’s the dirty secret of diffusion models: they don’t run a single expensive computation, they run it many times per generation. 50 steps means 50 full forward passes through a multi-billion-parameter transformer. That’s a lot of GPU hours burned …