Commit Graph

  • b7f3a10910 refactor: migrate __init_subclass__ to Metaclass Aaron 2023-05-26 15:20:51 -07:00
  • 150ea33d2d infra: bump to dev version [generated] aarnphm-ec2-dev 2023-05-26 23:17:41 +00:00
  • 26df699a03 feat(tools): add release script aarnphm-ec2-dev 2023-05-26 21:29:57 +00:00
  • ee3d17fdfa infra: prepare for 0.0.3 release Aaron 2023-05-26 00:19:47 -07:00
  • 85252f13c4 fix(cli): simplify register code for start Aaron 2023-05-26 01:44:33 -07:00
  • 4127961c5c feat: openllm.client aarnphm-ec2-dev 2023-05-26 07:17:28 +00:00
  • ac933d60f1 fix(cli): Make sure to skips models that only runs on GPU aarnphm-ec2-dev 2023-05-25 23:32:42 +00:00
  • 9cdc3545aa build(deps): Bump bufbuild/buf-setup-action from 1.17.0 to 1.19.0 (#2) dependabot[bot] 2023-05-25 16:23:04 -07:00
  • fed17fafdc migrate(configuration): remove deprecated max_length in favor of max_new_tokens aarnphm-ec2-dev 2023-05-25 23:19:45 +00:00
  • b502703f67 fix(chatglm): make sure to check for required dependencies cpm_kernels aarnphm-ec2-dev 2023-05-25 23:19:06 +00:00
  • 5c416fa218 feat: StarCoder aarnphm-ec2-dev 2023-05-25 23:15:55 +00:00
  • 3fe6b14dbf fix(cli): make sure __main__ is not convoluted aarnphm-ec2-dev 2023-05-25 23:08:10 +00:00
  • 765c1a6e5c feat: requires_gpu for specific LLM. aarnphm-ec2-dev 2023-05-25 23:05:20 +00:00
  • 83a8a7cb4f docs(codegen): make sure the generated dostring is correct aarnphm-ec2-dev 2023-05-25 23:00:34 +00:00
  • 20b3a0260f refactor: move Prompt object to client specific attributes aarnphm-ec2-dev 2023-05-25 22:58:25 +00:00
  • 545515c01f infra: Install BentoML from main and its auxilary dependencies aarnphm-ec2-dev 2023-05-25 22:57:19 +00:00
  • 73d152fc77 feat(gpu): Make sure that we run models on GPU if available aarnphm-ec2-dev 2023-05-25 02:10:36 +00:00
  • 135bafacaf fix(chatglm): support MacOS deployment Aaron 2023-05-24 05:05:48 -07:00
  • 9139360426 fix(coverage): Make sure to exclude the correct TYPE_CHECKING in openllm aarnphm-ec2-dev 2023-05-24 11:32:06 +00:00
  • 2676085b59 feat: chatglm and configuration naming type Aaron 2023-05-24 04:19:49 -07:00
  • 11c7783a0e fix(infra): feature_request.yml missing title Aaron Pham 2023-05-23 16:54:38 -07:00
  • 427106df98 fix(infra): bug_report.yml missing title Aaron Pham 2023-05-23 16:54:09 -07:00
  • 162c021cae feat(timeout): support server_timeout and LLM timeout Aaron 2023-05-23 16:48:01 -07:00
  • b1c07946c1 feat: dolly-v2 and general cleanup Aaron 2023-05-23 14:27:27 -07:00
  • a63cec8fa3 improve(flan-t5): update default generation config Aaron 2023-05-16 12:20:38 -07:00
  • 602294b782 fix(start): silence error logs for now Aaron 2023-05-16 12:19:23 -07:00
  • 549b0c54e9 feat: codegen and bundle build Aaron 2023-05-15 16:16:58 -07:00
  • d31d450526 feat: Adding central service definition and init openllm_client Aaron 2023-05-15 00:33:05 -07:00
  • 2a53faee9c infra: add structure and cleanup separation of tokenizer Aaron 2023-05-05 11:57:39 -07:00
  • 426a61713f feat: start and start_grpc API Aaron 2023-05-05 02:40:51 -07:00
  • 3e32b24194 feat: initial openllm_client implementation Aaron 2023-05-04 22:59:59 -07:00
  • dd8b6050b2 feat: FLAN-T5 supports Chaoyu 2023-04-18 17:27:53 -07:00