Commit graph

  • 8bbc15830e Merge branch 'main' of https://github.com/santiagxf/llama-stack into santiagxf/azure-ai-inference Facundo Santiago 2024-11-11 21:15:27 +00:00
  • 2b21e97624 feat: refactor code base Facundo Santiago 2024-11-11 21:14:52 +00:00
  • ca2cd71182 tests w/ eval params Xi Yan 2024-11-11 16:01:21 -05:00
  • f8f95dad1f remove 8b_correctness scoring_fn from tests Xi Yan 2024-11-11 15:55:09 -05:00
  • b1ebc837f8 refactor scoring Xi Yan 2024-11-11 15:49:18 -05:00
  • a6038ffee9 refactor scoring Xi Yan 2024-11-11 15:48:07 -05:00
  • aa66410f24 localfs -> LocalFS Xi Yan 2024-11-11 15:37:29 -05:00
  • 68a4e6d00e fix scoring test Xi Yan 2024-11-11 15:33:56 -05:00
  • e27c6e3662 fix datasetio Xi Yan 2024-11-11 15:29:29 -05:00
  • acd055d763 rename evals related stuff Xi Yan 2024-11-11 15:11:07 -05:00
  • 2b7d70ba86
    [Evals API][11/n] huggingface dataset provider + mmlu scoring fn (#392) Xi Yan 2024-11-11 14:49:50 -05:00
  • 1050617c56 openapi gen Xi Yan 2024-11-11 14:01:24 -05:00
  • b78ee3a0a5
    fix duplicate deploy in compose.yaml (#417) Suraj Subramanian 2024-11-11 13:51:14 -05:00
  • 0d9d3f07a6
    fix duplicate deploy in compose.yaml Suraj Subramanian 2024-11-11 13:46:53 -05:00
  • c1f7ba3aed
    Split safety into (llama-guard, prompt-guard, code-scanner) (#400) Ashwin Bharambe 2024-11-11 09:29:18 -08:00
  • 4971113f92 Update provider_type -> inline::llama-guard in templates, update run.yaml Ashwin Bharambe 2024-11-11 09:12:17 -08:00
  • 15ffceb533 more fixes (some fixes to pre-existing issues in safety fixture) Ashwin Bharambe 2024-11-11 09:09:47 -08:00
  • fdfc37a878 huggingface -> remote adapter Xi Yan 2024-11-11 12:02:17 -05:00
  • 7507cd487f rebase on top of Dinesh's refactor Ashwin Bharambe 2024-11-11 08:46:20 -08:00
  • a7f728e41c small fix Ashwin Bharambe 2024-11-07 16:01:36 -08:00
  • 984ba074e1 add deprecation_error pointing meta-reference -> inline::llama-guard Ashwin Bharambe 2024-11-07 15:23:15 -08:00
  • fdaec91747 Split safety into (llama-guard, prompt-guard, code-scanner) Ashwin Bharambe 2024-11-07 14:35:04 -08:00
  • e9a9ecb2dc comments Xi Yan 2024-11-11 11:07:12 -05:00
  • 9ff903e63b delete preregistered dataset/eval task Xi Yan 2024-11-11 11:05:47 -05:00
  • 8bebe3fd1f register to client Xi Yan 2024-11-11 11:03:01 -05:00
  • 75ccc05296 rename Xi Yan 2024-11-11 10:48:47 -05:00
  • 1031f1404b add register model to unit test Xi Yan 2024-11-11 10:35:59 -05:00
  • e690eb7ad3 Merge branch 'main' into mmlu_benchmark Xi Yan 2024-11-11 10:22:32 -05:00
  • 6d38b1690b
    added quickstart w ollama and toolcalling using together (#413) Justin Lee 2024-11-09 10:52:26 -08:00
  • e8fd45f9f0 corrected url for colab Justin Lee 2024-11-09 10:23:07 -08:00
  • b0b9c905b3 docs Xi Yan 2024-11-09 10:22:41 -08:00
  • 95c8339a3f added quickstart w ollama and toolcalling using together Justin Lee 2024-11-09 10:18:42 -08:00
  • cc61fd8083 docs Xi Yan 2024-11-09 09:00:18 -08:00
  • 0c14761453 docs Xi Yan 2024-11-09 08:57:51 -08:00
  • 4986e46188
    Distributions updates (slight updates to ollama, add inline-vllm and remote-vllm) (#408) Ashwin Bharambe 2024-11-08 18:09:39 -08:00
  • 211a7f8f28 Write some docs Ashwin Bharambe 2024-11-08 18:02:43 -08:00
  • 38cdbdec5a add inline-vllm details, fix things Ashwin Bharambe 2024-11-08 12:01:05 -08:00
  • 02c66b49fc remote vllm distro Ashwin Bharambe 2024-11-08 11:32:06 -08:00
  • ba82021d4b precommit Xi Yan 2024-11-08 17:58:58 -08:00
  • 1ebf6447c5 add missing inits Xi Yan 2024-11-08 17:54:24 -08:00
  • 89c3129f0b add missing inits Xi Yan 2024-11-08 17:49:29 -08:00
  • f6aaa9c708 Bump version to 0.0.50 Xi Yan 2024-11-08 17:28:39 -08:00
  • 65371a5067
    [Docs] Zero-to-Hero notebooks and quick start documentation (#368) Justin Lee 2024-11-08 17:16:44 -08:00
  • ec644d3418
    migrate model to Resource and new registration signature (#410) Dinesh Yeduguru 2024-11-08 16:12:57 -08:00
  • d6a9a17828 address feedback Dinesh Yeduguru 2024-11-08 16:11:53 -08:00
  • 6f3b2bb815 quick start typeddict Justin Lee 2024-11-08 15:33:06 -08:00
  • 6569b1c840 changed colab url to reflect main Justin Lee 2024-11-08 15:06:32 -08:00
  • cc29fc0fe8 implemented check health for cloud client Justin Lee 2024-11-08 15:04:18 -08:00
  • 022f20e710 fixed based on ashwin comments Justin Lee 2024-11-08 15:01:13 -08:00
  • 4f367cbf6b remove network host Xi Yan 2024-11-08 14:55:04 -08:00
  • c79c8367b7 pr review changes Justin Lee 2024-11-08 14:50:44 -08:00
  • 490f7e9a75 refactor Xi Yan 2024-11-08 14:19:55 -08:00
  • 772e23e29e register singature fix Dinesh Yeduguru 2024-11-08 14:15:31 -08:00
  • 23777abeb7 working tests Dinesh Yeduguru 2024-11-08 14:10:40 -08:00
  • 8cd7e406c0 docker compose commands Xi Yan 2024-11-08 14:00:54 -08:00
  • bd0622ef10 update docs Xi Yan 2024-11-08 12:46:43 -08:00
  • 4f5c4d1e3b add back llama_model field Dinesh Yeduguru 2024-11-07 21:40:54 -08:00
  • ca88f3f182 resource oriented object design for models Dinesh Yeduguru 2024-11-07 16:43:55 -08:00
  • 5625aef48a
    Add pip install helper for test and direct scenarios (#404) Dalton Flanagan 2024-11-08 15:18:21 -05:00
  • d800a16acd
    Resource oriented design for shields (#399) Dinesh Yeduguru 2024-11-08 12:16:11 -08:00
  • fe072620c8 address feedback Dinesh Yeduguru 2024-11-08 12:00:36 -08:00
  • 9d04f11543 remove todo Xi Yan 2024-11-08 11:43:15 -08:00
  • 58c6138df1 move dataset to hf llamastack repo Xi Yan 2024-11-08 11:42:16 -08:00
  • 0eaca98229 improved registration flow Dinesh Yeduguru 2024-11-08 11:07:41 -08:00
  • 39f0c5f544 minor updates Dinesh Yeduguru 2024-11-07 22:40:15 -08:00
  • 04a2965967 right naming Dinesh Yeduguru 2024-11-07 22:24:45 -08:00
  • 19d57b4d82 dont add together fixture Dinesh Yeduguru 2024-11-07 21:07:38 -08:00
  • b5d130fe2a use correct shield impl in meta ref Dinesh Yeduguru 2024-11-07 21:04:08 -08:00
  • 874206baeb add register in meta reference Dinesh Yeduguru 2024-11-07 20:59:16 -08:00
  • 932b524449 use env vars for bedrock guardrail vars Dinesh Yeduguru 2024-11-07 20:15:42 -08:00
  • 98c09323a9 bedrock test for inference fixes Dinesh Yeduguru 2024-11-07 15:24:45 -08:00
  • e0f227f23c working bedrock tests Dinesh Yeduguru 2024-11-07 14:57:12 -08:00
  • d960f9b60f init Dinesh Yeduguru 2024-11-07 12:09:14 -08:00
  • 6dd5ea7631 added colab links to each notebook Justin Lee 2024-11-08 10:38:03 -08:00
  • 7ee9f8d8ac rename Xi Yan 2024-11-08 10:34:48 -08:00
  • b1d7376730 kill tgi/cpu Xi Yan 2024-11-08 10:33:45 -08:00
  • d8cea721ca elaborate on distributions Justin Lee 2024-11-08 10:30:36 -08:00
  • fc6c39b598 additional instructions in quickstart Justin Lee 2024-11-08 10:25:25 -08:00
  • 7a4fa9e30d change model-size, consolidate setup, formating changes Justin Lee 2024-11-08 09:56:52 -08:00
  • 731644e111 pre-commit Dalton Flanagan 2024-11-08 12:51:24 -05:00
  • 05d9e5465f reorganized file names Justin Lee 2024-11-08 08:58:33 -08:00
  • 92f16ed27b changed from vision to text model Justin Lee 2024-11-08 08:57:38 -08:00
  • efb0fbfaea tool calling changes Justin Lee 2024-11-08 08:52:15 -08:00
  • 14dff9745d tool calling changes Justin Lee 2024-11-08 08:32:35 -08:00
  • 75f742775d Merge branch 'main' of https://github.com/santiagxf/llama-stack into santiagxf/azure-ai-inference Facundo Santiago 2024-11-08 15:04:48 +00:00
  • c07919aa36 remove print Dalton Flanagan 2024-11-08 08:20:11 -05:00
  • 33ea496cf9 pip install helptext Dalton Flanagan 2024-11-08 08:18:32 -05:00
  • 72b2c885ee openapi gen Xi Yan 2024-11-07 23:17:10 -08:00
  • 8b018c4b78 gen openapi Xi Yan 2024-11-07 22:26:38 -08:00
  • e178081be5 Use the list endpoint instead of ps to get ollama's models Geronimo De Abreu 2024-11-08 00:40:18 -05:00
  • d42774c41b msg Xi Yan 2024-11-07 21:36:49 -08:00
  • 989f070bc0 move benchmark task def to file Xi Yan 2024-11-07 21:35:02 -08:00
  • f429e75b3e fix tests Xi Yan 2024-11-07 21:31:05 -08:00
  • 0443b36cc1 merge Xi Yan 2024-11-07 21:27:08 -08:00
  • 6192bf43a4
    [Evals API][10/n] API updates for EvalTaskDef + new test migration (#379) Xi Yan 2024-11-07 21:24:12 -08:00
  • 0dc2b9c6e4 fixture return impl Xi Yan 2024-11-07 21:22:18 -08:00
  • 9076221924 resource oriented object design for models Dinesh Yeduguru 2024-11-07 16:43:55 -08:00
  • 0297111dfd dont add together fixture Dinesh Yeduguru 2024-11-07 21:07:38 -08:00
  • 49b68942e8 use correct shield impl in meta ref Dinesh Yeduguru 2024-11-07 21:04:08 -08:00
  • d66293d498 add register in meta reference Dinesh Yeduguru 2024-11-07 20:59:16 -08:00