vLLM
Everything Fervor AI has published that touches vLLM — 3 pieces, newest first.
-
vLLM Constrained Decoding Fixes the Tool Calls Your Self-Hosted Agent Keeps Breaking
Most broken tool calls from a self-hosted agent model are a serving setting rather than a model flaw, because vLLM only forces tool calls into the declared schema when a…
-
Briefing · October 26, 2026 · afternoon
Agent actions keep getting cheaper to produce, and the most useful builder posts of the day control the action itself, at decode time or at the sandbox or the push,…
-
Top-1 Token Flips: How Your vLLM Backend and Quantization Choice Change What the Model Says
Identical weights served through different attention backends and quantizations produce measurably different tokens, so the quality you get from a local model is a…