v0.3.7-python

• Changes from v0.5.2-rust

v0.5.1-rust

• Add #substrs docs.
• max_state_id is now correctly computed with respect to #substrs
• Make Python FFI docs safety section more comprehensive

v0.5.0-rust

• Make EngineLike a sealed trait so adding more methods to it will not break compatibility.
• Support new syntax: #substrs"xxxxx" which supports generating one substring out of a long string.

v0.3.6-python

• The case of all tokens are allowed is now handled without UB in the fast path of mask_logits for torch tensor
• Add safety checks to guard against the fast path of mask_logits so mask_logits does not lead to UB on platforms where usize is not 64 bit.
• Update docs to align with implementations of Engine
• Changes from v0.5.1-rust

v0.3.5-python

• Make torch mask_logits significantly faster by bypassing unreasonably slow Python interpreter & allowed token ids index->allowed token ids CPU tensor cache
• Changes from v0.5.0-rust

v0.3.4-python

• Make compute_allowed_token_ids no-gil. In other words, it no longer blocks python threads.
• Changes from v0.4.3-rust

v0.4.3-rust

• Cache invalid bytes for token skipping when computing allowed tokens

v0.4.2-rust

• Reuse the computation of first byte when computing allowed tokens

v0.3.2-python

• Changes from v0.4.2-rust

v0.4.1-rust

• If a token can be accepted by the engine but also completes the engine in the middle of accepting, the token will now be fully accepted.