v1.2.0
What's Changed
- add cuda all image to facilitate deployment by @OlivierDehaene in #186
- add splade pooling to Bert by @OlivierDehaene in #187
- support vertex api endpoint by @drbh in #184
- readme examples by @plaggy in #180
- add_pooling_layer for bert classification by @OlivierDehaene in #190
- add /embed_sparse route by @OlivierDehaene in #191
- Applying
Cargo.toml
optimization options by @somehowchris in #201 - Add Dockerfile-arm64 to allow docker builds on Apple M1/M2 architecture by @iandoe in #209
- configurable payload limit by @OlivierDehaene in #210
- add api_key for request authorization by @OlivierDehaene in #211
- add all methods to vertex API by @OlivierDehaene in #192
- add
/decode
route by @OlivierDehaene in #212 - Input Types Compatibility with OpenAI's API (#112) by @OlivierDehaene in #214
New Contributors
- @drbh made their first contribution in #184
- @plaggy made their first contribution in #180
- @somehowchris made their first contribution in #201
- @iandoe made their first contribution in #209
Full Changelog: v1.1.0...v1.2.0