Model Releases
How we built the most performant DeepSeek V3.2, MiniMax-M2.5 and Qwen 3.5 397B on DigitalOcean Serverless Inference
DigitalOcean describes their optimization and deployment of three large language models (DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B) on their Serverless Inference platform, likely leveraging NVIDI
DigitalOcean describes their optimization and deployment of three large language models (DeepSeek V3.2, MiniMax-M2.5, and Qwen 3.5 397B) on their Serverless Inference platform, likely leveraging NVIDIA Blackwell Ultra hardware for performance improvements. The article covers the technical implementation, optimization techniques, and infrastructure decisions that enabled efficient inference serving for these advanced models. This represents DigitalOcean's approach to making cutting-edge LLMs accessible through their managed serverless platform.
Source: DigitalOcean | 2026-04-28