Tool Call Accuracy

vLLM 0.31 adds constrained decoding to fix tool-call schema errors

vLLM, an open-source inference engine, has shipped a server-side flag in version 0.31 that enables constrained decoding, a technique forcing model output to match a required schema. The post's authors say that serving Kimi K2.6 on vLLM 0.28 produced correctly formatted tool calls only 92% of the time, but enabling the new flag raised accuracy to 100% for newer Kimi and DeepSeek models.