Released a patch that set the upper bound for cattrs<23.2, which breaks our whole serialisation process both upstream and downstream.
What's Changed
- fix: StreamingResponse compatibility issue by @xianml in #4248
- bentocloud doc update --data field by @MingLiangDai in #4272
- docs: Add repository and bento selection notes by @Sherlock113 in #4280
- fix(dispatcher): unbounded overload batch_size by @aarnphm in #4273
- docs: update transformers example to include gpu options by @ssheng in #4281
- fix monitoring docs configuration.yaml typo by @KimSoungRyoul in #4287
- fix: runnable framework logic in transformers.py by @benfu-verses in #4291
- docs: Update docs on supported CUDA versions by @Sherlock113 in #4288
- docs: Add docs for new transformers model import API by @Sherlock113 in #4282
- fix: Disable exception in serve-grpc on Windows in development mode by @zimka in #4294
- fix(dependencies): lock cattrs<23.2 for now by @aarnphm in #4292
New Contributors
- @benfu-verses made their first contribution in #4291
- @zimka made their first contribution in #4294
Full Changelog: v1.1.9...v1.1.10