v0.2.6

Highlights since v0.2.5:

• Harden input validation, deserialization, and worker-thread error handling so invalid inputs raise exceptions instead of crashing the process (#869). Preserve tokenizer JSON round trips, including binary vocabulary and token-grammar compilation (#879).
• Extend EBNF and Lark grammars with capture, lazy matching, suffix/stop conditions, token and character budgets, and sampling temperature options. Add Lark regex flags, structured substring expressions, and a cached GrammarCompiler.compile_lark API.
• Improve grammar compilation with direct JSON Schema AST construction, shared FSM construction, in-place optimizer passes, and cached parser-state properties.
• Add Cohere XML, Kimi K3, and EXAONE 4.0 structural tags, plus max_tokens / max_chars support for AnyTextFormat and AnyTokensFormat.
• Fix JSON carriage-return whitespace, positional prefixItems handling, NUL regex rejection, repeat-edge metadata, and grammar serialization keys.
• Add an NPU token-bitmask backend and Windows ARM64 wheels. Reduce Python wheel size and expand the documentation.

Full changelog: v0.2.5...v0.2.6

Note: this is not the release version of the prior v0.2.6rc1 and v0.2.6rc2. Instead, it covers all the updates in the main branch since v0.2.5. Their official version will be released in the next version.