EPISODE · Jan 5, 2026 · 5 MIN
Goodput, Not Just Throughput: Prefill, Decode, and Rethinking AI Inference
from Intellectually Curious · host Mike Breault
We unpack the core bottleneck in streaming AI: the split between heavy pre-fill computations and fast, memory-light decoding. From chunked prefill to physical separation (DissServe) and logical isolation (DuetServe), we explore how phase isolation eliminates interference, delivering 2x–4.5x better goodput and transforming cost efficiency. Join us as we translate GPU architecture ideas into scalable, user-friendly AI services, with practical takeaways for builders, operators, and decision-makers.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
What this episode covers
We unpack the core bottleneck in streaming AI: the split between heavy pre-fill computations and fast, memory-light decoding. From chunked prefill to physical separation (DissServe) and logical isolation (DuetServe), we explore how phase isolation eliminates interference, delivering 2x–4.5x better goodput and transforming cost efficiency. Join us as we translate GPU architecture ideas into scalable, user-friendly AI services, with practical takeaways for builders, operators, and decision-make...
NOW PLAYING
Goodput, Not Just Throughput: Prefill, Decode, and Rethinking AI Inference
No transcript for this episode yet
Similar Episodes
No similar episodes found.