Anchor talk: ₹11 lakh/month: how we took the GPU out of Face Match

Vivek Kalyanarangan, Sr. Technical Architect, AI at IDfy

Beyond GPUs: cutting ML inference costs by 10× without sacrificing latency

Vivek Kalyanarangan, Sr. Technical Architect at IDfy

Decoding at a million tokens when the KV cache lives in host memory: what actually bounds the step

Vivek Kalyanarangan, Head of AI at IDfy