Inference Engineering
How to make neural network models perform inference optimally.
Runs from March 20th - April 10th 2027.
Facilitators
What it covers
-
How inference works
Details prefill and decoding stages.
-
Inference Hardware
Covers the role of GPUs, CPUs, and Memory
-
Inference Software
From low-level (CUDA), frameworks (PyTorch), hosting and serving (vLLM, Ollama, SGLang)
-
Techniques
Covers prefix caching, KV caching, Batching, etc.
Signups aren't open yet — express interest and we'll email you when your place can be confirmed.
Express interest