NVIDIA inference expert on when to keep, repurpose or replace aging GPUs
kimmonismus · x · 2026-10-11
The author interviewed Shruti Koparkar of NVIDIA, who works on accelerated computing and AI inference. Topics covered: CUDA and CUDA-X, the economics of AI infrastructure, and how long GPUs stay useful and profitable as models and workloads change — when to keep an older system, when to repurpose or replace it, and the role software plays in that decision. Full interview to be uploaded soon.
More from Infra
- Let's Encrypt moves to 64-day certificate lifetimes by default in Feb 2027 — jedisct1 · 2026-10-11
- Anthropic engineer hits 1 billion tokens per day for a week — AaronBergman18 · 2026-10-11
- Independent Researcher Makes TPU Pallas top-k Bitwise Correct and 1.67x Faster — Francis_YAO_ · 2026-10-11
- AI agent tunes Triton kernels on AMD MI210, flipping grid order yields 1.29x speedup — zmkzmkz · 2026-10-11
- Engineer with $120k of GPUs: bought 75% before the price surge, don't follow me — TheZachMueller · 2026-10-11
- Migrating AI workloads often means 70%+ redevelopment, warns cloud analyst — DavidLinthicum · 2026-10-11