Posts
How we run GPU infrastructure with agents, from meeting to merge
Extending GPU fractions to a B200 hit an immutable node selector
How NVLink, RDMA rails and GPUDirect Storage fit together
KAI Resource Management accepts GPU quotas that do not add up
I tried to win the office footy tipping with my own AI model
How we halved search latency without changing a single ranking
How we patch a production GPU cluster with an AI agent
Why systemctl daemon-reload drops GPUs from running Kubernetes pods
Resolving the Harbor uid 10000 vs FreeIPA admin collision on Kubernetes
Handing one node's GPUs to HAMi without touching the live models
The Answer Was Already in Teams. We Just Couldn't Find It.
How my document classifier votes before it ever asks a language model
How I Built ASI's Marketing Engine Around AI Agents
From XGBoost to LightGBM: How Our ML Model Adapted to Two Market Regimes
- Announcing the Ollama GPU Calculator