AI Inference

NVIDIA Vera Rubin NVL72 makes its debut in MLPerf Inference v6.1, breaking performance records across large language model serving workloads. Analyze system architecture, software stack optimizations, FP4 throughput, and inference economics.

AI inference startup Baseten is reportedly finalizing a massive funding round, highlighting the shift from model training to large-scale inference infrastructure in the enterprise sector.

Baseten is reportedly securing a massive $1.5 billion funding round, signaling a major shift in the AI market from model training to large-scale inference infrastructure.

AI inference startup Baseten is reportedly finalizing a massive $1.5 billion funding round at a $13 billion valuation, signaling a massive shift from training-heavy investments to the 'inference gold rush'.

AI chip startup Groq is reportedly raising $650 million in new funding as it pivots from a pure hardware model to an 'Inference-as-a-Service' powerhouse, aiming to outpace Nvidia in real-time LLM performance.

AI chip startup Groq is reportedly raising $650 million to pivot from a hardware-only model to a high-speed AI inference service provider, directly competing with Nvidia's dominance.

Explore the physics of AI reasoning through the lens of Self-Organized Criticality (SOC) and learn how to leverage these emergent capabilities using high-performance APIs.

In a historic shift from IP licensing to silicon production, Arm unveils the Arm AGI CPU specifically designed for AI inference and agentic workloads in partnership with Meta.

Microsoft has introduced its latest custom AI silicon, the Maia chip, featuring 100 billion transistors and specialized 4-bit precision performance to drastically reduce LLM inference costs and latency.