Commit Graph

  • 79c9608735 infra: reduce wait time to around 7 mins (#726) Aaron Pham 2023-11-22 07:28:36 -05:00
  • 831bb8c497 infra: bump to homebrew tap release to 0.4.26 [generated] [skip ci] Aaron Pham 2023-11-22 11:59:36 +00:00
  • 80842ad501 infra: bump to dev version of 0.4.27.dev0 [generated] [skip ci] Aaron Pham 2023-11-22 11:58:42 +00:00
  • 7eae50377d infra: prepare for release 0.4.26 [generated] [skip ci] v0.4.26 Aaron Pham 2023-11-22 11:50:50 +00:00
  • b28b5269b5 feat(openai): chat templates and complete control of prompt generation (#725) Aaron Pham 2023-11-22 06:49:14 -05:00
  • 7aa0918a6f fix(client): correct schemas parser from correct response output (#724) Aaron Pham 2023-11-22 05:01:35 -05:00
  • f83f64ffd7 fix(infra): setup higher timer for building container images (#723) Aaron Pham 2023-11-22 05:00:33 -05:00
  • 6dd07580e2 infra: bump to homebrew tap release to 0.4.25 [generated] [skip ci] Aaron Pham 2023-11-22 09:35:41 +00:00
  • 1876609a67 infra: bump to dev version of 0.4.26.dev0 [generated] [skip ci] Aaron Pham 2023-11-22 09:34:22 +00:00
  • 0189342730 infra: prepare for release 0.4.25 [generated] [skip ci] v0.4.25 Aaron Pham 2023-11-22 09:22:45 +00:00
  • 63d86faa32 fix(openai): correct stop tokens and finish_reason state (#722) Aaron Pham 2023-11-22 04:21:13 -05:00
  • 06626e7d1e infra: bump to homebrew tap release to 0.4.24 [generated] [skip ci] Aaron Pham 2023-11-22 06:51:39 +00:00
  • c9b23638a5 infra: bump to dev version of 0.4.25.dev0 [generated] [skip ci] Aaron Pham 2023-11-22 06:50:35 +00:00
  • 7f09f9daf2 infra: prepare for release 0.4.24 [generated] [skip ci] v0.4.24 Aaron Pham 2023-11-22 06:34:30 +00:00
  • d697ea3903 fix(image): setup correct installation Aaron 2023-11-22 01:33:26 -05:00
  • 9f84b8b945 infra: bump to homebrew tap release to 0.4.23 [generated] [skip ci] Aaron Pham 2023-11-22 06:26:20 +00:00
  • 1df549f76a infra: bump to dev version of 0.4.24.dev0 [generated] [skip ci] Aaron Pham 2023-11-22 06:25:32 +00:00
  • 85e03a4b92 infra: prepare for release 0.4.23 [generated] [skip ci] v0.4.23 Aaron Pham 2023-11-22 06:16:49 +00:00
  • 38b7c44df0 fix(base-image): update base image to include cuda for now (#720) Aaron Pham 2023-11-22 01:15:19 -05:00
  • 8bb2742a9a chore(types): append additional types change (#719) Aaron Pham 2023-11-21 22:38:20 -05:00
  • 04ef08a7f8 chore(strategy): compact and add stubs (#718) Aaron Pham 2023-11-21 21:49:28 -05:00
  • 909db8c3bf refactor: reduce compiled cacheline Aaron Pham 2023-11-22 02:27:42 +00:00
  • 77bd6f090a chore(logger): fix warnings and streamline style (#717) Aaron Pham 2023-11-21 18:54:51 -05:00
  • d53cf234bd fix(api-server): correct set generation from LLM class Aaron Pham 2023-11-21 10:38:36 +00:00
  • 2821e172ef fix(examples): use non-chat models Aaron Pham 2023-11-21 10:11:35 +00:00
  • 93709f1d66 fix(infra): remove unless exclude Aaron 2023-11-21 05:04:47 -05:00
  • 14242a7ab8 fix(utils): correct import Aaron 2023-11-21 05:03:20 -05:00
  • c33b071ee4 refactor: delete unused code (#716) Aaron Pham 2023-11-21 04:39:48 -05:00
  • a8a9f154ce fix(ci): tests (#715) Aaron Pham 2023-11-21 03:05:22 -05:00
  • e70246ca5d feat(generation): add support for eos_token_id (#714) Aaron Pham 2023-11-21 02:01:36 -05:00
  • fde78a2c78 chore: cleanup unused prompt templates (#713) Aaron Pham 2023-11-21 01:56:51 -05:00
  • e6b9a749a4 infra: bump to homebrew tap release to 0.4.22 [generated] [skip ci] Aaron Pham 2023-11-21 01:50:09 +00:00
  • be7a4bf576 infra: bump to dev version of 0.4.23.dev0 [generated] [skip ci] Aaron Pham 2023-11-21 01:49:02 +00:00
  • f3fd32d596 infra: prepare for release 0.4.22 [generated] [skip ci] v0.4.22 Aaron Pham 2023-11-21 01:38:46 +00:00
  • ad4f388c98 refactor: update runner helpers and add max_model_len (#712) Aaron Pham 2023-11-20 20:37:15 -05:00
  • 8fc5f1f70c infra: bump to homebrew tap release to 0.4.21 [generated] [skip ci] Aaron Pham 2023-11-20 22:50:00 +00:00
  • aac92f40ac infra: bump to dev version of 0.4.22.dev0 [generated] [skip ci] Aaron Pham 2023-11-20 22:48:59 +00:00
  • 4c4bc82a47 infra: prepare for release 0.4.21 [generated] [skip ci] v0.4.21 Aaron Pham 2023-11-20 22:32:44 +00:00
  • 00e2666e48 fix(build): contraint packages for bentoml >1.1.10 Aaron 2023-11-20 17:30:21 -05:00
  • 1f2cdc8021 chore(deps): bump github/codeql-action from 2.22.5 to 2.22.7 (#707) dependabot[bot] 2023-11-20 17:22:49 -05:00
  • 62da3a7fe5 chore(deps): bump docker/build-push-action from 5.0.0 to 5.1.0 (#708) dependabot[bot] 2023-11-20 17:22:41 -05:00
  • b1ee1ce2a1 chore(deps): bump taiki-e/install-action from 2.21.11 to 2.21.17 (#709) dependabot[bot] 2023-11-20 17:22:30 -05:00
  • d7bb0ab197 ci: pre-commit autoupdate [pre-commit.ci] (#711) pre-commit-ci[bot] 2023-11-20 17:22:19 -05:00
  • c25f69fddc infra: bump to homebrew tap release to 0.4.20 [generated] [skip ci] Aaron Pham 2023-11-20 22:19:49 +00:00
  • 5491fe30b0 infra: bump to dev version of 0.4.21.dev0 [generated] [skip ci] Aaron Pham 2023-11-20 22:18:14 +00:00
  • 204cbd43d2 infra: prepare for release 0.4.20 [generated] [skip ci] v0.4.20 Aaron Pham 2023-11-20 22:09:47 +00:00
  • f753662ae6 fix(build): only load model when eager is True Aaron 2023-11-20 17:06:25 -05:00
  • 5b92e848e2 fix: raises error if backend is not supported Aaron 2023-11-20 17:03:30 -05:00
  • 3769ca73a9 infra: bump to homebrew tap release to 0.4.19 [generated] [skip ci] Aaron Pham 2023-11-20 08:19:58 +00:00
  • 82ee9e845a infra: bump to dev version of 0.4.20.dev0 [generated] [skip ci] Aaron Pham 2023-11-20 08:19:02 +00:00
  • 46d6fcca98 infra: prepare for release 0.4.19 [generated] [skip ci] v0.4.19 Aaron Pham 2023-11-20 08:06:53 +00:00
  • 12b2b8ed21 fix: remove prompt template Aaron Pham 2023-11-20 08:04:40 +00:00
  • 41c857f292 fix: set correct type annotations Aaron Pham 2023-11-20 07:17:38 +00:00
  • 7e2aa80a8c infra: bump to homebrew tap release to 0.4.18 [generated] [skip ci] Aaron Pham 2023-11-20 05:25:42 +00:00
  • d82896a80c infra: bump to dev version of 0.4.19.dev0 [generated] [skip ci] Aaron Pham 2023-11-20 05:24:31 +00:00
  • c1f86bda16 infra: prepare for release 0.4.18 [generated] [skip ci] v0.4.18 Aaron Pham 2023-11-20 05:15:14 +00:00
  • 513c08ccda feat(openai): dynamic model_type registration (#704) Aaron Pham 2023-11-20 00:13:45 -05:00
  • 6505abdb44 chore: update lower bound version of bentoml to avoid breakage (#703) Aaron Pham 2023-11-19 23:09:14 -05:00
  • ed01080c1b infra: bump to homebrew tap release to 0.4.17 [generated] [skip ci] Aaron Pham 2023-11-20 03:55:05 +00:00
  • 7b89fde99e infra: bump to dev version of 0.4.18.dev0 [generated] [skip ci] Aaron Pham 2023-11-20 03:54:07 +00:00
  • d1915d7a9e infra: prepare for release 0.4.17 [generated] [skip ci] v0.4.17 Aaron Pham 2023-11-20 03:43:21 +00:00
  • 4491aa54d0 fix(backend): correct use variable for backend when initialisation (#702) Aaron Pham 2023-11-19 22:42:25 -05:00
  • 44f05da845 infra: update generate notes and better local handle (#701) Aaron Pham 2023-11-19 17:50:23 -05:00
  • 83f95c74ff infra: bump to homebrew tap release to 0.4.16 [generated] [skip ci] Aaron Pham 2023-11-19 15:53:11 +00:00
  • 184c6739d1 infra: bump to dev version of 0.4.17.dev0 [generated] [skip ci] Aaron Pham 2023-11-19 15:50:55 +00:00
  • e9207ff683 infra: prepare for release 0.4.16 [generated] [skip ci] v0.4.16 Aaron Pham 2023-11-19 15:41:03 +00:00
  • cb4386b013 fix(release): remove unecessary check for client dependencies [skip ci] Aaron 2023-11-19 10:38:59 -05:00
  • 1968704b71 chore: update changelog [skip ci] (#700) Aaron Pham 2023-11-19 10:30:48 -05:00
  • d80c392661 chore: update documentation about runtime (#699) Aaron Pham 2023-11-19 10:27:07 -05:00
  • 816c1ee80e feat(engine): CTranslate2 (#698) Aaron Pham 2023-11-19 10:25:08 -05:00
  • 539f250c0f feat(vllm): bump to 0.2.2 (#695) Aaron Pham 2023-11-19 02:52:32 -05:00
  • 206521e02d feat(ctranslate): initial infrastructure support (#694) Aaron Pham 2023-11-19 01:48:33 -05:00
  • 93ffb29e9f infra: bump to homebrew tap release to 0.4.15 [generated] [skip ci] Aaron Pham 2023-11-19 00:57:03 +00:00
  • 4d3e221168 infra: bump to dev version of 0.4.16.dev0 [generated] [skip ci] Aaron Pham 2023-11-19 00:56:11 +00:00
  • c19654adf3 infra: prepare for release 0.4.15 [generated] [skip ci] v0.4.15 Aaron Pham 2023-11-19 00:47:18 +00:00
  • 099cc22a94 chore: update documentation (#693) Aaron Pham 2023-11-18 19:44:52 -05:00
  • 1831d8f129 feat: heuristics logprobs (#692) Aaron Pham 2023-11-18 19:26:20 -05:00
  • 4499469efb fix(annotations): check library through find_spec (#691) Aaron Pham 2023-11-18 02:02:16 -05:00
  • e9a89b7a7e fix(cattrs): strictly lock <23.2 until we upgrade validation logic (#690) Aaron Pham 2023-11-17 17:11:15 -05:00
  • 3d204e9cea infra: bump to homebrew tap release to 0.4.14 [generated] [skip ci] Aaron Pham 2023-11-17 22:07:26 +00:00
  • 781ae72c6f infra: bump to dev version of 0.4.15.dev0 [generated] [skip ci] Aaron Pham 2023-11-17 22:04:01 +00:00
  • 5402db1e61 infra: prepare for release 0.4.14 [generated] [skip ci] v0.4.14 Aaron Pham 2023-11-17 21:54:10 +00:00
  • 0891cde0b6 fix(dependencies): ignore broken cattrs release (#689) Aaron Pham 2023-11-17 16:52:58 -05:00
  • 131f3f5dc3 infra: bump to homebrew tap release to 0.4.13 [generated] [skip ci] Aaron Pham 2023-11-17 21:18:13 +00:00
  • 1c5d07d60c infra: bump to dev version of 0.4.14.dev0 [generated] [skip ci] Aaron Pham 2023-11-17 21:17:18 +00:00
  • e14f3ffed5 infra: prepare for release 0.4.13 [generated] [skip ci] v0.4.13 Aaron Pham 2023-11-17 21:06:56 +00:00
  • c03e3bebb3 fix(infra): prepare correct dependencies for release [skip ci] (#687) Aaron Pham 2023-11-17 16:02:25 -05:00
  • 80ed400646 fix(build): lock lower version based on each release and update infra (#686) Aaron Pham 2023-11-17 15:57:31 -05:00
  • e01f93f0c3 examples: improve instructions and cleanup simple API server (#684) Aaron Pham 2023-11-17 11:53:56 -05:00
  • 381d740a7a fix(llm): remove unnecessary check (#683) Aaron Pham 2023-11-17 11:23:22 -05:00
  • 10471f7e4e infra: bump to homebrew tap release to 0.4.12 [generated] [skip ci] Aaron Pham 2023-11-17 16:05:37 +00:00
  • 89c49f3a4f infra: bump to dev version of 0.4.13.dev0 [generated] [skip ci] Aaron Pham 2023-11-17 16:04:37 +00:00
  • 65370f6919 infra: prepare for release 0.4.12 [generated] [skip ci] v0.4.12 Aaron Pham 2023-11-17 15:54:41 +00:00
  • 14b3ceb436 fix(torch_dtype): correctly infer based on options (#682) Aaron Pham 2023-11-17 10:52:05 -05:00
  • 7402408c5f fix(envvar): explicitly set NVIDIA_DRIVER_CAPABILITIES (#681) Aaron Pham 2023-11-17 10:40:45 -05:00
  • bd513e51a8 infra: bump to homebrew tap release to 0.4.11 [generated] [skip ci] Aaron Pham 2023-11-17 15:04:54 +00:00
  • 122c95dc31 infra: bump to dev version of 0.4.12.dev0 [generated] [skip ci] Aaron Pham 2023-11-17 15:03:29 +00:00
  • 5752c3f0d8 infra: prepare for release 0.4.11 [generated] [skip ci] v0.4.11 Aaron Pham 2023-11-17 14:53:12 +00:00
  • bce273ad47 fix(env): correct format environment on docker (#680) Aaron Pham 2023-11-17 09:51:17 -05:00
  • c1e0e3eae7 fix(build): correctly parse default env for container (#679) Aaron Pham 2023-11-17 09:35:26 -05:00