Tested 2026-08-08 with LiquidAI/LFM2.5-2.6B.
Both engines translate the model's tool call into JSON incrementally, while the model is still generating. That translation goes wrong whenever the arguments contain characters needing escapes. The two engines fail on complementary inputs, and in opposite ways.
| argument payload | vLLM v0.26.0 (--tool-call-parser lfm2) | llama.cpp b10156 (--jinja) |