How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design
-
Purnima Kumari
DigitalOCean
Sr. Solutions Architect II
By 2026, the cloud-only AI paradigm will be obsolete. Discover how open-weight models and dynamic quantization are making powerful local inference the default for secure enterprise workflows.
Checking access…
Playback and chapters load privately for Free videos.
Jobs that call for the skills explored in this talk.