Speculation is all you need: Intro to Speculative Decoding for High Performance Inference
Registration
About Event
When it comes to low-latency, high performance inference, speculation is all you need.
Join us for a webinar with Shankha Biswas, who has worked with DFlash and EAGLE3 draft models on Modal's inference optimization team. Learn the basics of speculative decoding while understanding when draft models can help unlock major leaps in inference efficiency.
We'll dive into:
Inference performance with and without speculative decoding
Training draft models (EAGLE3 → custom speculators)
Lessons from Modal’s work with Decagon
Resources to get started