DeepSeek flash model documents a legacy Pentaho ETL setup and plans its migration
l4rz · x · 2026-10-29
l4rz reports ds4flash-0731 cleared his reference task: given a tarball of configs and logs from a legacy Pentaho ETL setup, the model documented every still-running ETL process down to individual SQL queries and planned the migration to something modern. Photo shows a rack of ASUS mini PCs used as a local inference cluster.
More from Infra
- Evo 2 genomic model now runs on vLLM: 7B fits 1-megabase context on a single H100 — anshulkundaje · 2026-10-30
- Meta's GenRecs Tokenization lifts ad conversions +0.35% with semantic vocabulary — Meta_Engineers · 2026-10-30
- Parallel Language Models paper: multi-token generation at AR quality, up to 5.7x speedup — aaron_lou · 2026-10-30
- Oracle investor day: 1GW AI site earns ~$80B contract value at ~28% ROI, 3.6-year payback — rohanpaul_ai · 2026-10-30
- Sam Altman: Local inference is a terrible allocation of scarce global compute — morqon · 2026-10-30
- AWS blueprint: deploy NVIDIA Nemotron 3.5 Super VL (120B MoE) on EKS with Dynamo and vLLM — AWS ML Blog · 2026-10-30