42 versions

• Fix support for containers w/ CUDA 13.0+ (#831)no API changesb38b8f12026-02-17 20:56
• Update `version` to 1.9.0 (#830)no API changes56992472026-02-17 13:26
• Add `--served-model-name` for OpenAI requests via HTTP (#685)○102f60f02026-01-21 14:14
• Update `version` to 1.8.3 (#745)no API changes78502d82025-10-30 09:02
• Update `version` to 1.8.2 (#716)no API changesd7af1fc2025-09-09 14:31
• Update `version` to 1.8.1 (#712)no API changes0adb0002025-09-04 15:18
• Update `docs/openapi.json` for v1.8.0 (#708)●31○14b22dd5c2025-09-01 17:55
• Preparing the update to 1.7.1 (#623)no API changes006e16b2025-06-03 13:38
• Preparing for release 1.7.0 (candle update + modernbert). (#570)no API changes72dac202025-04-08 11:47
• v1.6.0 (#448)no API changes5a5adc72024-12-12 14:47
• v1.5.1no API changesbbde2032024-11-05 14:42
• docs: Rename 'Sentence Transformers' to 'sentence-transformers' in docstrings (#342)no API changesaf89c272024-07-15 15:53
• v1.5.0 (#336)no API changes661a77f2024-07-10 15:33
• feat: add `/similarity` route (#331)○1e496fe72024-07-08 10:24
• v1.4.0no API changesa0549e62024-07-02 15:16
• feat: add default prompts (#312)▲5○2303614792024-06-28 10:07
• v1.2.3no API changescc1c5102024-04-25 08:47
• v1.2.2no API changes22f6fd72024-04-16 14:23
• v1.2.1no API changes89270932024-04-15 16:57
• Change license to Apache 2.0 (#231)no API changes3c385a42024-04-08 13:07
• v1.2.0 (#215)no API changes3edace22024-03-22 16:35
• feat: add `/decode` route (#212)▲2○290ea6642024-03-22 14:19
• feat: add all methods to vertex API (#192)○1a57cf612024-03-21 16:44
• feat: add /embed_sparse route (#191)○27efa6972024-03-07 10:51
• v1.1.0no API changesca99fa32024-02-29 14:43
• v1.0.0 (#168)no API changes41b692d2024-02-23 16:10
• fix: add cors_allow_origin to cli (#162)no API changes00a17ea2024-02-22 11:20
• feat(router): add /tokenize route (#139)▲1○16395a7a2024-01-26 17:57
• v0.6.0no API changes28281272023-11-30 14:27
• fix: hf hub redirects (#89)no API changese10e10e2023-11-24 16:52
• misc: rename passage to text▲1●3○288c5b542023-11-20 15:25
• v0.5.0no API changesc0209ff2023-11-20 15:18
• feat: rerank route (#84)○18e85e9c2023-11-20 15:07
• feat: accept batches in predict (#78)▲3○236161c12023-11-16 13:42
• v0.4.0no API changesb41601c2023-11-15 18:17
• feat: add support for classification models (#76)▲2○44e1f5cd2023-11-15 17:41
• v0.3.0no API changesc7d758d2023-10-27 12:45
• v0.2.1no API changes021899d2023-10-18 17:38
• v0.2.0no API changesbd34ca52023-10-18 11:38
• feat: add `--pooling` arg (#14)○17af5bd62023-10-16 19:49
• v0.1.0▲13●4○38b26fd462023-10-13 13:40
• 1.9.3latest2026-07-17 12:05