vLLM Collaborates with DigitalOcean to Host Kimi K3 Model
vllm_project · x · 2026-07-28
The vLLM project announced a collaboration with DigitalOcean to run the Kimi K3 model. Kimi K3 is now live on the DigitalOcean Inference Engine, featuring 1M-token context and native vision. It is built to run agentic tasks for hours with no setup or model ops required.
More from Infra
- Kimi K3 lands on Fireworks AI for inference and training — omarsar0 · 2026-07-28
- YC expands AI startup support with $25k compute credits and a GPU cluster — ycombinator · 2026-07-28
- Amazon and Microsoft will each spend about $200B on AI data centers this year — fortune · 2026-07-28
- AMD says Instinct MI455X will deliver 34x MI355X token throughput — Beth_Kindig · 2026-07-28
- Google Cloud adds near-real-time billing anomaly alerts for Gemini API and Vertex AI — rseroter · 2026-07-28
- Block Attention Residuals cuts attention overhead from O(Ld) to O(Nd) — stochasticchasm · 2026-07-28