pub fn prefix_caching_active(
enable_flag: bool,
kv_only_prefix_cache_is_safe: bool,
) -> boolExpand description
2026-09-25: Whether the prefix cache the server will install is a real cache: the
flag and ModelConfig::kv_only_prefix_cache_is_safe, the predicate
build_prefix_cache uses. Preflight calls this before the cache exists;
TransformerModel::new asks the constructed cache (PrefixCache::is_active).