Posts tagged "Qwen"

Codex CLI against a self-hosted Qwen3.8-27B-NVFP4 on vLLM worked fine for exactly one turn, then started throwing a raw 400 the moment a tool call came back: 'System message must be at the beginning.' Here's the trail from a stale config comment, through vLLM's Responses API internals, into the model's own Jinja chat template, and the upstream GitHub issue that told me not to patch vLLM at all — but to override the template instead.