Commit graph

  • cb719891b9 Docs improvement v3 (#433) Justin Lee 2024-11-22 15:43:31 -08:00
  • 6c21b41b36 model -> model_id for TGI Ashwin Bharambe 2024-11-22 15:40:08 -08:00
  • 1f7bd4f5b7 More doc cleanup Ashwin Bharambe 2024-11-22 14:37:22 -08:00
  • 32fbe366d7 opentelemetry upload to dataset Dinesh Yeduguru 2024-11-27 14:09:24 -08:00
  • 2dfbb9744d explicit type for trace Dinesh Yeduguru 2024-11-27 09:24:23 -08:00
  • dfe152cb97 endpoint to bulk export traces for eval Dinesh Yeduguru 2024-11-26 22:09:49 -08:00
  • b3e149334a fixes Dinesh Yeduguru 2024-11-26 15:41:08 -08:00
  • af8a1fe5b3 tracing for APIs Dinesh Yeduguru 2024-11-26 14:07:48 -08:00
  • c2a4850a79 tracing decorator for apiis Dinesh Yeduguru 2024-11-26 11:28:24 -08:00
  • c6b4bf8ada add endpoint to export traces and standerdize the span creation Dinesh Yeduguru 2024-11-25 16:01:52 -08:00
  • 54bc5f2d55 add more attributes for inference, shields and memory Dinesh Yeduguru 2024-11-25 13:31:30 -08:00
  • b3021ea2da explicit span management using with Dinesh Yeduguru 2024-11-25 13:07:43 -08:00
  • 6411007024 add memory bank attributes Dinesh Yeduguru 2024-11-25 11:54:40 -08:00
  • 316f0423ab Update links in the README file (distributions table) Vladimir Ivic 2024-11-26 23:26:47 -08:00
  • b1a63df8cd
    move playground ui to llama-stack repo (#536) Xi Yan 2024-11-26 22:04:21 -08:00
  • 371259ca5b readme Xi Yan 2024-11-26 22:02:29 -08:00
  • 8840cf1d9a readme Xi Yan 2024-11-26 20:16:39 -08:00
  • 2c8a7a972c rename playground-ui -> ui Xi Yan 2024-11-26 20:15:41 -08:00
  • d467638f26 move playground ui to llama-stack repo Xi Yan 2024-11-26 19:57:00 -08:00
  • c2cfd2261e move playground ui to llama-stack repo Xi Yan 2024-11-26 19:54:24 -08:00
  • 15e21cb8bd temp commit Botao Chen 2024-11-26 19:52:10 -08:00
  • 060b4eb776
    allow env NVIDIA_BASE_URL to set NVIDIAConfig.url (#531) Matthew Farrellee 2024-11-26 20:46:44 -05:00
  • 50cc165077
    fixes tests & move braintrust api_keys to request headers (#535) Xi Yan 2024-11-26 13:11:21 -08:00
  • 193028e3b1 add env to fixtures Xi Yan 2024-11-26 13:10:31 -08:00
  • 5e635d2e64 fix eval test Xi Yan 2024-11-26 13:04:33 -08:00
  • e01d6d793c api keys refactor Xi Yan 2024-11-26 12:45:13 -08:00
  • 9a976bcabd temp commit Botao Chen 2024-11-26 10:49:03 -08:00
  • bc427b3081
    Merge branch 'main' into groq Swan Htet Aung 2024-11-26 12:28:31 -06:00
  • 8a56f916ab add nvidia nim inference provider to docs Matthew Farrellee 2024-11-26 12:06:22 -05:00
  • 6d41a93188 add completion api support Matthew Farrellee 2024-11-25 09:55:14 -05:00
  • a772b1a599 add test for completion logprobs Matthew Farrellee 2024-11-26 10:19:29 -05:00
  • 1708ab1225 allow env NVIDIA_BASE_URL to set NVIDIAConfig.url Matthew Farrellee 2024-11-26 10:10:05 -05:00
  • 4b9085d312
    Merge branch 'main' into clarifai-inference-provider sanjaychelliah 2024-11-26 18:01:45 +05:30
  • 5fba02da29 . Aidan Do 2024-11-26 11:06:03 +00:00
  • 85ae899964 . Aidan Do 2024-11-26 10:49:48 +00:00
  • f6f3f3c792 . Aidan Do 2024-11-26 10:29:46 +00:00
  • 5a845cebfd . Aidan Do 2024-11-26 10:05:00 +00:00
  • f946d23d8e . Aidan Do 2024-11-26 10:00:38 +00:00
  • 1801aa145d [#391] Add support for json structured output for vLLM Aidan Do 2024-11-26 09:40:17 +00:00
  • d3956a1d22 fix description Xi Yan 2024-11-25 22:02:45 -08:00
  • 2936133f95 precommit Xi Yan 2024-11-25 18:55:54 -08:00
  • 74a6aa2c81 add groq inference provider Benjamin Klieger 2024-11-25 17:54:14 -08:00
  • d7598c68d7 temp commit Botao Chen 2024-11-25 17:27:26 -08:00
  • bbd81231ce add missing __init__ Xi Yan 2024-11-25 17:23:27 -08:00
  • de7af28756
    Tgi fixture (#519) Dinesh Yeduguru 2024-11-25 13:17:02 -08:00
  • e2d1b712e2 Testing - Memory provider fakes Vladimir Ivic 2024-11-25 10:24:52 -08:00
  • b7b764f8c8 make TGI_API_TOKEN optional in fixture Dinesh Yeduguru 2024-11-25 10:06:39 -08:00
  • 60cb7f64af add missing __init__ Xi Yan 2024-11-25 09:42:27 -08:00
  • bbea9bccf1 Revert provider / inference config back to mainline Connor Hack 2024-11-25 09:20:27 -08:00
  • 8d83759caf Add MODEL_CHECKPOINT_DIR check after update Connor Hack 2024-11-25 08:10:04 -08:00
  • 659764b91f Update documentation Henry Tu 2024-11-25 08:07:38 -08:00
  • db9c28b885 Regenerate distro codegen Henry Tu 2024-11-25 07:58:04 -08:00
  • 5de4c8bfe0 Regenerate distro codegen Henry Tu 2024-11-25 07:57:56 -08:00
  • 3838bd1704 Cerebras Integration Henry Tu 2024-11-20 10:20:28 -08:00
  • ac1974353c Revert fork target back to main Connor Hack 2024-11-25 07:46:09 -08:00
  • 1912ff2341 Temporarily make repo point to fork for PR testing Connor Hack 2024-11-25 07:30:51 -08:00
  • 107cd20e2b reduce the accuracy requirements to pass the chat completion structured output test Matthew Farrellee 2024-11-25 10:22:33 -05:00
  • cd0c80d61f Add env vars debug printout Connor Hack 2024-11-25 07:13:54 -08:00
  • e428b82398 Revert test formula Connor Hack 2024-11-25 06:44:55 -08:00
  • 217f81bdb1
    Merge branch 'meta-llama:main' into main Chacksu 2024-11-25 09:38:35 -05:00
  • 43116efe4d Changed Indentation which was causing error Sarthak Deshpande 2024-11-25 16:26:30 +05:30
  • 9cb73d564b Optimized number of redis calls Sarthak Deshpande 2024-11-25 16:10:04 +05:30
  • 44b3f90d13 Added /alpha to api endpoints of client file to represent the latest API endpoint Sarthak Deshpande 2024-11-25 15:05:24 +05:30
  • e4f11296b6 minor fix on unregister api param Sixian Yi 2024-11-25 01:19:47 -08:00
  • 1d33b8e733 Replaced zrangebylex method in the range method Sarthak Deshpande 2024-11-25 14:31:41 +05:30
  • 58d664ab31 unregister api for dataset Sixian Yi 2024-11-22 19:44:23 -08:00
  • 7e6a11d17b fix tgi to correctly pass llama model Dinesh Yeduguru 2024-11-24 21:12:57 -08:00
  • 34be07e0df Ensure model_local_dir does not mangle "C:\" on Windows Ashwin Bharambe 2024-11-24 14:18:59 -08:00
  • 7d7d1e6ea1
    Merge branch 'meta-llama:main' into groq Swan Htet Aung 2024-11-24 03:51:45 -06:00
  • d8d0f4600d Adds groq inference adapter swanhtet1992 2024-11-24 03:50:26 -06:00
  • 0f73a4a829 Add groq inference adapter. swanhtet1992 2024-11-24 03:27:05 -06:00
  • 8920c4216f Implement additional functionality supported by Sambanova. swanhtet1992 2024-11-24 01:55:36 -06:00
  • a82eb97bdf init: docker build for ssambanova seyeong-han 2024-11-24 01:42:25 -06:00
  • 839f4a4779 feat: add INFERENCE_MODEL env seyeong-han 2024-11-24 01:41:55 -06:00
  • 1d3cc0b138 fix: api_key to api_token seyeong-han 2024-11-24 01:38:55 -06:00
  • 73b51308d3 fix: model to model_id seyeong-han 2024-11-24 01:31:47 -06:00
  • 09490e4ee3 init: ssambanova template seyeong-han 2024-11-24 01:30:09 -06:00
  • 061a1cc790 fix: message.content can be None seyeong-han 2024-11-24 01:20:04 -06:00
  • 3cace74458 Add inference test fixture for tgi Dinesh Yeduguru 2024-11-23 22:52:06 -08:00
  • 9ddda91180 Add Safety section for Configuration Ashwin Bharambe 2024-11-23 21:36:19 -08:00
  • b6a79d6291 Implement SambaNova as new remote API Provider. swanhtet1992 2024-11-23 21:32:05 -06:00
  • 4e6c984c26
    add NVIDIA NIM inference adapter (#355) Matthew Farrellee 2024-11-23 18:59:00 -05:00
  • a7df3e539c feat: add ssambanova provider seyeong-han 2024-11-23 17:55:04 -06:00
  • 2cfc41e13b Mark some pages as not-in-toctree explicitly Ashwin Bharambe 2024-11-23 15:27:44 -08:00
  • 4d6351ae2c init: ssambanova inference seyeong-han 2024-11-23 14:58:37 -06:00
  • 358db3c5b6 No need to use os.path.relpath() when Path() knows everything anyway Ashwin Bharambe 2024-11-23 11:45:47 -08:00
  • a23960663d Upgrade README a bit Ashwin Bharambe 2024-11-23 09:36:30 -08:00
  • 45fd73218a Bump version to 0.0.55 v0.0.55 Ashwin Bharambe 2024-11-23 09:03:58 -08:00
  • 359effd534 Update DirectClient docs for 0.0.55 Ashwin Bharambe 2024-11-23 09:01:55 -08:00
  • 707da55c23 Fix TGI register_model() issue Ashwin Bharambe 2024-11-23 08:47:05 -08:00
  • 01ae720a7b Add integration test for redis memory provider Mohit Gaur 2024-11-23 11:28:58 +00:00
  • 4b94cd313c Simplify Docs intro even further Ashwin Bharambe 2024-11-23 00:14:16 -08:00
  • 0758eb9cb1 Try new llama stack image Ashwin Bharambe 2024-11-23 00:03:42 -08:00
  • 03efc89267 Make a new llama stack image Ashwin Bharambe 2024-11-22 23:49:22 -08:00
  • fc8ace50af Add stub for Building Applications Ashwin Bharambe 2024-11-22 23:05:17 -08:00
  • c7bfac5382 Add a section for run.yamls Ashwin Bharambe 2024-11-22 22:58:39 -08:00
  • 1e6006c599 More simplification of the "Starting a Llama Stack" doc Ashwin Bharambe 2024-11-22 22:38:53 -08:00
  • 76fc5d9f31
    Update Ollama supported llama model list (#483) Martin Hickey 2024-11-23 05:56:43 +00:00
  • 039e303707 docs fix Xi Yan 2024-11-22 21:15:21 -08:00
  • 988f424c9c
    [docs] evals (#511) Xi Yan 2024-11-22 21:09:39 -08:00