Stories
Inference
Stories curated for Inference
Artificial Intelligence
DeepSeek Open-Sources DeepInfer, Its Production Inference Engine
DeepSeek released DeepInfer under Apache 2.0 on October 20, 2026, the inference framework powering its V4.1-Flash model at scale on NVIDIA SM100 and Huawei Ascend 950 hardware.
AI
Microsoft Sets 2027 Start for Maia 300 as Azure Plans Multi-Gigawatt AI Inference
Microsoft says Maia 300 production deployments will begin in 2027, as it scales its custom AI-accelerator program for inference across Azure.