litellm v1.110.2
litellm v1.110.2
Verify Docker Image Signature
cosign verify \
--certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
ghcr.io/berriai/litellm:v1.110.2
What’s Changed
- fix(router): do not retry a Responses stream after an output item reached the client (#52461) [stable/1.110.x] by @kerry-berri in https://github.com/BerriAI/litellm/pull/52690
- fix(router): backport the Rust router memory fix to stable/1.110.x by @kerry-berri in https://github.com/BerriAI/litellm/pull/52463
- fix: backport #52313, #52341 and #52350 to stable/1.110.x for v1.110.1 by @kerry-berri in https://github.com/BerriAI/litellm/pull/52469
- fix(responses): prevent stream restarts after non-text output (#52616) [stable/1.110.x] by @kerry-berri in https://github.com/BerriAI/litellm/pull/52751
- fix(key-management): backport #52838 and #52925 to stable/1.110.x and cut 1.110.2 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/52938
- fix(responses): cache bridged system prompts on stored GPT-6.2 requests (backport #52906 to 1.110) by @mateo-berri in https://github.com/BerriAI/litellm/pull/52920
Full Changelog: https://github.com/BerriAI/litellm/compare/v1.110.1…v1.110.2
Source BerriAI/litellm ·
v1.110.2· 2026-11-20 · upstream release
Mirrored verbatim for indexing. All rights belong to the upstream project.
Release notes are published by the upstream project and mirrored here for indexing. All rights belong to their authors.