https://www.blog.graceg.co/p/rethinking-open-source-contributionThe 180en2026-05-26T06:36:51+00:00Rethinking Open Source Contribution in the Age of AI Agents, featuring vLLM Core Maintainer Roger Wang at MLSys 2026https://www.blog.graceg.co/p/tpus-vs-gpus-what-they-are-how-theyThe 180en2026-05-26T06:35:24+00:00TPUs vs. GPUs: What They Are, How They Differ, and Which Workloads Belong on Eachhttps://www.blog.graceg.co/p/vllm-on-google-cloud-tpu-a-modelThe 180en2026-05-26T06:33:22+00:00vLLM on Google Cloud TPU: A Model Size vs Chip Cheat Sheet (With Interactive Tool)https://www.blog.graceg.co/p/google-cloud-tpu-architecture-versionsThe 180en2026-05-24T20:13:48+00:00Google Cloud TPU Architecture Versions Explained: From v1 to the Eighth Generation