My agent commits code every day. The lazy way to wire that up is an SSH key — a credential with no scope, no revocation, and no trail. Here is the self-hosted git forge I put in front of prod instead, the traps that bit during the migration, and the last layer I honestly haven't built yet.
#ai#opsec#self-hosting#git#agent-security
IT & SystemsNov 14, 20269 min The sequel to 'Memory is a workload'. Extraction is chatty and latency-sensitive; consolidation is a nightly, quality-hungry monster. One lane served both and lost both — so the pipeline got two machines, one silent env-variable trap, one 504 storm, and an honest single point of failure.
#local-llm#memory#homelab#self-hosted
IT & SystemsNov 9, 20266 min The same Qwen3.8-Flash-Next quant landed on my Strix Halo and my 1080 Ti on the same day. Same weights, same release notes — completely different optimization problems. Here is the sizing math, the receipts, and the three ops traps I fell into while upgrading both.
#unsloth#quantization#strix-halo#1080-ti#gufo#strata#qwen
IT & SystemsNov 7, 20267 min CUDA 13 stopped compiling for Pascal — the third formal death notice for my 1080 Ti fallback. Before accepting it I ran a proper A/B campaign on the engine: one free 20 % decode win, one flag I kept on bitwise-parity evidence, three I rejected as noise, and two measurements I distrust even now.
#gpu#nvidia#pascal#cuda#local-llm#benchmarking#strata
IT & SystemsNov 3, 20267 min Persistent memory for a local assistant is not a storage problem — it is an inference-load problem. Gateway lanes, a retain storm, a literal *** bug, and a doctrine reversal, all inside 48 hours.
#local-llm#memory#homelab#litellm
ElectronicsNov 1, 20266 min NVIDIA sent Pascal to the legacy driver branch. EVGA itself left the GPU business. The card got two death notices and answered with receipts — including the time I caught my own first draft's numbers being wrong and re-measured everything.
#gpu#nvidia#pascal#local-llm#reliability#benchmarking