Tag: vllm

All the articles with the tag "vllm".

• Ten bugs, two-tenths of a point — the weekend search got measurably better

  1 Jun, 2026

  A weekend search-quality sprint that took benchmark scores from 0.67 to 0.74, an MCP transport migration that cut cold starts by 96%, ten bugs found along the way, and a CVSS 9.4 Harbor CVE caught by an automation pipeline deployed the same day — with the benchmark research that made it all measurable.

• Streaming Journals: Kafka Meets LLMs

  11 Feb, 2026

  The automated journal entries were fiction. Every single one. Here's how a broken pipeline got replaced in 10 days — Kafka, vLLM workers, nine code iterations, a context preservation fix, and an LLM-as-Judge quality gate — all tracked through git commits and vault evidence.

• The Migration Question: When K3s Meets Reality

  5 Oct, 2025

  K3s was already running. The question wasn't whether to use it - it was whether to migrate everything to it. A day of deep research revealed the hidden cost of containerization.