Commit graph

  • b8fdeb7873 init registry once Dinesh Yeduguru 2024-11-13 15:17:33 -08:00
  • e90ea1ab1e
    make distribution registry thread safe and other fixes (#449) Dinesh Yeduguru 2024-11-13 15:12:34 -08:00
  • 40b55ed0d0 make distribution registry thread safe and other fixes Dinesh Yeduguru 2024-11-13 14:47:30 -08:00
  • 3b61c31dab add --max-parallel option Ashwin Bharambe 2024-11-13 14:03:17 -08:00
  • 15dee2b8b8
    Added link to the Colab notebook of the Llama Stack lesson on the Llama 3.2 course on DLAI (#445) Jeff Tang 2024-11-13 13:59:41 -08:00
  • a98dca12a9 bump buffer size Ashwin Bharambe 2024-11-13 13:58:53 -08:00
  • 4dc9624818 Support parallel downloads for llama model download Ashwin Bharambe 2024-11-13 13:41:07 -08:00
  • 787e2034b7
    model registration in ollama and vllm check against the available models in the provider (#446) Dinesh Yeduguru 2024-11-13 13:04:06 -08:00
  • 7e4765c45b address feedback Dinesh Yeduguru 2024-11-13 13:02:45 -08:00
  • 7f6ac2fbd7 allow seeing warnings with traces optionally Ashwin Bharambe 2024-11-13 12:27:19 -08:00
  • 96b1bafcde remove self in construction Dinesh Yeduguru 2024-11-13 12:26:31 -08:00
  • f63d51963d make model registery a helper for ollama and vllm Dinesh Yeduguru 2024-11-13 12:24:18 -08:00
  • 3b68e6cbbe return model in vllm Dinesh Yeduguru 2024-11-13 12:20:08 -08:00
  • e272f8aa62 fix vllm registry Dinesh Yeduguru 2024-11-13 12:12:22 -08:00
  • a019011326 fix ollama registry Dinesh Yeduguru 2024-11-13 12:03:43 -08:00
  • 701b247121 typo fix and added link to the course Jeff Tang 2024-11-13 11:46:20 -08:00
  • 96e7ef646f
    add support for ${env.FOO_BAR} placeholders in run.yaml files (#439) Ashwin Bharambe 2024-11-13 11:25:58 -08:00
  • 7253ef5d0a removed a note about using together api key - may need when it has to be passed Jeff Tang 2024-11-13 11:17:20 -08:00
  • db4a84f154 update README with link to DLAI llama stack lesson Colab link Jeff Tang 2024-11-13 11:15:27 -08:00
  • 0b22c84bb7 check for nullish-ness Ashwin Bharambe 2024-11-13 11:08:31 -08:00
  • 4074fcf83c showcase using env vars Ashwin Bharambe 2024-11-13 10:55:33 -08:00
  • e5ef94ded8 allow default values and nicer errors Ashwin Bharambe 2024-11-13 10:20:02 -08:00
  • 5e9c2aa4cc add support for ${env.FOO_BAR} placeholders in run.yaml files Ashwin Bharambe 2024-11-12 23:41:51 -08:00
  • 838b8d4fb5
    PR-437-Fixed bug to allow system instructions after first turn (#440) Sarthak Deshpande 2024-11-14 00:04:04 +05:30
  • 94a6f57812
    change schema -> dataset_schema for register_dataset api (#443) Xi Yan 2024-11-13 11:17:46 -05:00
  • f31476541e tests fix Xi Yan 2024-11-13 11:13:32 -05:00
  • 4b77d26ece Merge branch 'main' into fix_schema_dataset_schema Xi Yan 2024-11-13 11:06:34 -05:00
  • ce6c641ebd openapi Xi Yan 2024-11-13 11:03:06 -05:00
  • 5925488de4 change schema -> dataset_schema in register_dataset API Xi Yan 2024-11-13 11:01:55 -05:00
  • d5b1202c83
    change schema -> dataset_schema (#442) Xi Yan 2024-11-13 10:58:12 -05:00
  • d1f758abf6 change schema -> dataset_schema Xi Yan 2024-11-13 10:52:16 -05:00
  • c29fa56dde
    add inline:: prefix for localfs provider (#441) Xi Yan 2024-11-13 10:44:39 -05:00
  • 360054d5c2 add inline:: prefix Xi Yan 2024-11-13 10:41:45 -05:00
  • 70e30891ec PR-437-Fixed a bug where turns were getting fetched randomly Sarthak Deshpande 2024-11-13 18:37:23 +05:30
  • e6e49e1bc6 PR-437-Fixed bug to allow system instructions after first turn Sarthak Deshpande 2024-11-13 14:53:17 +05:30
  • 36b052ab10 slightly update README.md Ashwin Bharambe 2024-11-12 22:11:46 -08:00
  • 12947ac19e
    Kill "remote" providers and fix testing with a remote stack properly (#435) Ashwin Bharambe 2024-11-12 21:51:29 -08:00
  • 1cb42d3060 rebase and fix some small breakage due to model -> model_id fix Ashwin Bharambe 2024-11-12 21:47:39 -08:00
  • 22aedd0277 fixed agent persistence test, more cleanup Ashwin Bharambe 2024-11-12 21:31:02 -08:00
  • 4f3b009980 undo some unintentional changes, clean up some stuff Ashwin Bharambe 2024-11-12 19:47:46 -08:00
  • 0121114a5d remote tests are functional! Ashwin Bharambe 2024-11-12 19:17:58 -08:00
  • 8b7be87bec More work towards making remote stacks usable from tests Ashwin Bharambe 2024-11-12 17:09:31 -08:00
  • 8645f8bc9e Refactor safety shield fixtures Ashwin Bharambe 2024-11-12 15:58:58 -08:00
  • 743da9690b Kill the notion of a "remote" / "passthrough" provider Ashwin Bharambe 2024-11-12 15:30:59 -08:00
  • 59a65e34d3
    Update new_api_provider.md Xi Yan 2024-11-13 00:02:13 -05:00
  • fdff24e77a
    Inference to use provider resource id to register and validate (#428) Dinesh Yeduguru 2024-11-12 20:02:00 -08:00
  • 1bb01f9346 remove model lookup class Dinesh Yeduguru 2024-11-12 20:00:48 -08:00
  • 606df220f5 fix evals and scoring Dinesh Yeduguru 2024-11-12 18:14:58 -08:00
  • 55d66ca918 run openapi gen Dinesh Yeduguru 2024-11-12 15:47:41 -08:00
  • e51107e019 Fix compose.yaml Ashwin Bharambe 2024-11-12 15:43:30 -08:00
  • 919d421bcf fixes after rebase Dinesh Yeduguru 2024-11-12 15:37:07 -08:00
  • 948f6ece6e fixes for all providers Dinesh Yeduguru 2024-11-12 14:25:28 -08:00
  • d5874735ea bedrock Dinesh Yeduguru 2024-11-12 14:08:47 -08:00
  • 92ee627e89 vllm Dinesh Yeduguru 2024-11-12 13:59:46 -08:00
  • 71219b4937 ollama Dinesh Yeduguru 2024-11-12 13:23:02 -08:00
  • 5b2282afd4 ollama and databricks Dinesh Yeduguru 2024-11-12 13:17:27 -08:00
  • 8de4cee373 working fireworks and together Dinesh Yeduguru 2024-11-12 13:07:35 -08:00
  • 25d8ab0e14 fix bedrock Dinesh Yeduguru 2024-11-12 10:17:51 -08:00
  • d69f4f8635 fix model provider validation and inference params Dinesh Yeduguru 2024-11-12 10:13:43 -08:00
  • 95b7f57d92 use provider resource id to validate for models Dinesh Yeduguru 2024-11-12 08:21:37 -08:00
  • e4f14eafe2 Use GPUs 0 and 1 Ashwin Bharambe 2024-11-12 14:21:22 -08:00
  • 1245a625ce Update vllm compose and run YAMLs Ashwin Bharambe 2024-11-12 12:46:32 -08:00
  • afe4a53ae8 Check vLLM registration Ashwin Bharambe 2024-11-12 13:14:36 -08:00
  • 1aeac7b9f7 Change order of building the Docker Ashwin Bharambe 2024-11-12 13:09:04 -08:00
  • 998419ffb2 use image tag actually! Ashwin Bharambe 2024-11-12 12:57:08 -08:00
  • 2c294346ae Update provider types and prefix with inline:: Ashwin Bharambe 2024-11-12 12:54:44 -08:00
  • 896b304e62 Use tags for docker images instead of changing image name Ashwin Bharambe 2024-11-12 12:42:11 -08:00
  • 983d6ce2df
    Remove the "ShieldType" concept (#430) Ashwin Bharambe 2024-11-12 12:37:24 -08:00
  • f246b5d98f lint Ashwin Bharambe 2024-11-12 12:35:16 -08:00
  • b94e6c0bd4 Fix Registry so it scopes keys by object types Ashwin Bharambe 2024-11-12 12:25:43 -08:00
  • b1c3a95485 Kill the notion of shield_type Ashwin Bharambe 2024-11-12 11:41:23 -08:00
  • 09269e2a44
    Enable sane naming of registered objects with defaults (#429) Ashwin Bharambe 2024-11-12 11:18:05 -08:00
  • 78d633123a regenerate OpenAPI, some small changes Ashwin Bharambe 2024-11-12 11:17:13 -08:00
  • 04d8660247 fix scoring fixture Ashwin Bharambe 2024-11-12 11:14:38 -08:00
  • d0ad198be9 fix Ashwin Bharambe 2024-11-12 11:11:01 -08:00
  • 593ba80162 fix MemoryBankInput Ashwin Bharambe 2024-11-12 10:28:41 -08:00
  • 48a6e27de9 Enable sane naming of registered objects with defaults Ashwin Bharambe 2024-11-12 10:17:34 -08:00
  • 9e925f43e5 print resources when booting up Ashwin Bharambe 2024-11-11 23:10:12 -08:00
  • 8363764093 Allow specifying resources in StackRunConfig Ashwin Bharambe 2024-11-11 22:08:51 -08:00
  • d9d271a684
    Allow specifying resources in StackRunConfig (#425) Ashwin Bharambe 2024-11-12 10:58:49 -08:00
  • ba8afa9235 print resources when booting up Ashwin Bharambe 2024-11-11 23:10:12 -08:00
  • abe1cc6303 Fix agents tests Ashwin Bharambe 2024-11-11 22:31:09 -08:00
  • 38257a9cbe Allow specifying resources in StackRunConfig Ashwin Bharambe 2024-11-11 22:08:51 -08:00
  • 8035fa1869 versioned persistence key prefixes Dinesh Yeduguru 2024-11-12 10:30:39 -08:00
  • cb77426fb5
    fix fireworks (#427) Xi Yan 2024-11-12 12:15:55 -05:00
  • dc0fa5afa9 fix fireworks Xi Yan 2024-11-12 12:09:23 -05:00
  • ec4fcad5ca
    fix eval task registration (#426) Xi Yan 2024-11-12 11:51:34 -05:00
  • acd0b0f3f6 fix eval tests Xi Yan 2024-11-12 11:49:48 -05:00
  • 6286970ee1 fix eval tasks Xi Yan 2024-11-12 11:43:10 -05:00
  • cb77712510 fix eval tasks Xi Yan 2024-11-12 11:42:49 -05:00
  • 84c6fbbd93
    fix tests after registration migration & rename meta-reference -> basic / llm_as_judge provider (#424) Xi Yan 2024-11-12 10:35:44 -05:00
  • ba1d50c67b naming fix Xi Yan 2024-11-12 10:29:25 -05:00
  • a15a4a4be2 rebase Xi Yan 2024-11-12 10:03:03 -05:00
  • 86fdad3be3
    Merge branch 'main' into restructure_scoring Xi Yan 2024-11-12 09:59:35 -05:00
  • 3d7561e55c
    Rename all inline providers with an inline:: prefix (#423) Ashwin Bharambe 2024-11-11 22:19:16 -08:00
  • f4426f6a43 Fix bug in llama stack build; SERVER_DEPENDENCIES were dropped Ashwin Bharambe 2024-11-11 20:12:13 -08:00
  • fd424e7900 util Xi Yan 2024-11-11 23:02:56 -05:00
  • 87dc116782 rename llm_as_judge, fix test Xi Yan 2024-11-11 22:57:51 -05:00
  • 506b99242a Allow specifying TEST / PYPI VERSION for docker name Ashwin Bharambe 2024-11-11 19:55:23 -08:00
  • e20dc8d133 impl rename Xi Yan 2024-11-11 22:41:54 -05:00