Notes from building and breaking infrastructure.https://stg-4a3c.et0.dev/https://stg-4a3c.et0.dev/posts/how-i-built-a-long-context-inference-service-on-eight-nvidia-b200-gpus/https://stg-4a3c.et0.dev/posts/how-i-built-a-long-context-inference-service-on-eight-nvidia-b200-gpus/For a few weeks, I had access to a rented server with eight NVIDIA B200 GPUs. The server had enough memory to load GLM-5.2, but loading the model was never the goal. I wanted three or four colleagues Wed, 05 Aug 2026 20:18:20 GMT