Posts tagged “inference-serving”
SGLang 0.5.21: Prefill–Decode Role-Switch Acceptance Checklist
An operator checklist for SGLang 0.5.21 role switching: qualify support, drain traffic, check graph headroom, verify execution and plan cache recovery.
An operator checklist for SGLang 0.5.21 role switching: qualify support, drain traffic, check graph headroom, verify execution and plan cache recovery.