Skip to content

v4.5.0

Choose a tag to compare

View all tags
@Nayjest Nayjest released this 14 Dec 20:40
· 306 commits to main since this release
v4.5.0
41a353d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's Changed

  • LLMContextLengthExceededError implemented (works for openai, google, anthropic)
  • llm / allm functions improvement: no retries in case of LLMContextLengthExceededError
  • run_parallel and llm_parallel now support additional arguments: allow_failures (bool) -- returns exceptions or values specified in return_on_failure argument in case of errors instead of raising it, log_errors (bool) -- specifies if error logging is needed (true by default)
  • fix using deprecated torch_dtype for mc.ApiType.TRANSFORMERS
  • local inference example added (Qwen 3 0.6B via hf/transformers)
  • infrastructure / gito.bot ai code reviewer: use latest Claude Sonnet 4.5 for GitHub PR code reviews

Full Changelog: v4.4.6...v4.5.0

Assets 2
Loading