How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design
-
Purnima Kumari
DigitalOCean
Sr. Solutions Architect II
The KV cache is the new memory bottleneck crippling generative AI applications. Learn how modern architectures like Grouped-Query Attention overcome this limit to optimize your production workloads.
Checking access…
Playback and chapters load privately for Free videos.
Jobs that call for the skills explored in this talk.