SGLang

Native decision-model serving since v0.5.21 (Oct 2, merged upstream Sept 25): both a /v1/decisions endpoint that converts any Jinja-templated chat model into a decision model and a /v1/systemone endpoint speaking the exact TypeSafe wire — official SDKs work by repointing the base URL. Any served generation model qualifies (validated on Qwen3.8-27B and Qwen3.5-35B-A3B, sub-100 ms decisions), no decision-specific training required. At ~38.6K stars the largest runtime the list covers; the stack xor pins its serving bundle to and openjev-sglang wraps, now first-class.