Commit graph

  • f47f7f1105 precommit Xi Yan 2025-04-05 20:01:47 -07:00
  • f9e45e6edf test inference Xi Yan 2025-04-05 19:59:10 -07:00
  • 5039888762 multiturn inference Xi Yan 2025-04-05 18:22:27 -07:00
  • 42251d2f28 fixing imports Raghotham Murthy 2025-04-05 13:40:32 -07:00
  • c8be228875
    chore(github-deps): bump thollander/actions-comment-pull-request dependabot[bot] 2025-04-05 20:09:14 +00:00
  • 4630b3b03b
    docs: Fix typo in README.md Francisco Arceo 2025-04-05 13:49:52 -06:00
  • 254319bc8c doc: llama4 getting started nb Eric Huang 2025-04-05 12:16:52 -07:00
  • 4c1c956a8c
    Update README.md Hardik Shah 2025-04-05 12:13:25 -07:00
  • 20cbcdf0d5 feat: introduce llama4 support Ashwin Bharambe 2025-04-05 09:39:05 -07:00
  • ee981a0c02 feat: adding mongodb vector_io module Ashwin Gangadhar 2025-02-19 21:48:05 +05:30
  • a98b5632cf
    Update docs/source/building_applications/agent_execution_loop.md Francisco Arceo 2025-04-03 22:41:55 -04:00
  • 1fef036373 fix typo Francisco Javier Arceo 2025-04-03 22:33:50 -04:00
  • db9eded18a docs: Some aesthetic changes to the Building AI Applicaitons to make them read a little easier Francisco Javier Arceo 2025-04-03 22:33:21 -04:00
  • 1df2988bed Fixing semantic issues Jamie Land 2025-04-03 13:31:03 -04:00
  • b4203226d6 fix: use model-id Jeff MAURY 2025-04-03 19:06:17 +02:00
  • 28b3f9ab83 : This is a combination of 3 commits. Jamie Land 2025-04-03 12:33:13 -04:00
  • 861962fa80 In progress: Add NVIDIA e2e notebook Jash Gulabrai 2025-04-03 11:19:43 -04:00
  • 0d79043d79 Fixed an error in the preprocessor type definition. ilya-kolchinsky 2025-04-03 12:51:00 +02:00
  • 0b968678b4 Fixed an error in the preprocessor type definition. ilya-kolchinsky 2025-04-03 12:49:50 +02:00
  • 863f87aa15 Restrict the changes to the new preprocessing API only. ilya-kolchinsky 2025-04-03 12:19:08 +02:00
  • 2008cd7921 Moving preprocessors.py to a separate directory. ilya-kolchinsky 2025-04-03 11:14:11 +02:00
  • bfece15fb4 docs: Fix incorrect link and command for generating API reference (#1124) Yuan Tang 2025-02-15 22:05:23 -05:00
  • 39030d5c14
    Update remote-vllm.md - format change AlexHe99 2025-04-03 14:06:39 +08:00
  • 39f33a42e5 fix: remove NEWLINE in README wesley chun 2025-04-02 17:53:50 -07:00
  • 8f75f6ad5d colorize Discord badge & add icon wesley chun 2025-04-02 17:43:36 -07:00
  • d51fa45821 fix(telemetry): unstructured log event warning Eric Huang 2025-04-02 16:24:03 -07:00
  • b8a5089eed
    Update importing_as_library.md Matthew Farrellee 2025-04-02 17:44:03 -04:00
  • 085cc7beed update get_apikey in adaptor get_params jhpiedrahitao 2025-04-02 15:43:14 -05:00
  • 47e5ae682b Fixing a mistake in the previous commit. ilya-kolchinsky 2025-04-02 19:57:22 +02:00
  • 60e9f46856 Merge-related changes. ilya-kolchinsky 2025-04-02 19:56:44 +02:00
  • 9f5543a643 feat: make training config fields optional Charlie Doern 2025-04-02 11:35:23 -04:00
  • ffb5600ec4 Revert requirements.txt to match commit b7ab1a9 Peter Double 2025-04-02 11:41:37 -04:00
  • 0a7f9e84f6 fix linting raspawar 2025-04-02 10:47:59 +00:00
  • c098cc3b99
    Merge branch 'meta-llama:main' into register_custom_model Rashmi Pawar 2025-04-02 16:14:52 +05:30
  • 27a1657118 update documentation raspawar 2025-04-02 10:04:12 +00:00
  • 3d2b374ee7 add register_model method raspawar 2025-04-02 09:51:55 +00:00
  • 5dc386c9b2
    Update remote-vllm.md AlexHe99 2025-04-02 15:34:15 +08:00
  • 80adc42614 fastapi_paths to tuple and simplified startswith check Peter Double 2025-04-01 22:31:32 -04:00
  • 9f3c1ed545 update getting started guide to use ollama pull Matthew Farrellee 2025-04-01 16:09:15 -04:00
  • a49549063a add comment about why ps vs list Matthew Farrellee 2025-04-01 15:21:20 -04:00
  • 3372301fa7 add litellm api_base param jhpiedrahitao 2025-04-01 11:55:38 -05:00
  • f08035c2fc chore: don't use asserts to guarantee self.model_store is not None Ihar Hrachyshka 2025-04-01 10:19:55 -04:00
  • d443607d65 chore: add some explanations and explicit check callouts to mypy ignores Ihar Hrachyshka 2025-04-01 10:08:27 -04:00
  • 5350aec461 ci: pin github actions to hashes Ihar Hrachyshka 2025-03-25 09:52:50 -04:00
  • 4e81b1e650 use ollama list to find models Matthew Farrellee 2025-04-01 09:41:35 -04:00
  • 9c9f9577e2 Merge branch 'main' into feat/litellm_sambanova_usage jhpiedrahitao 2025-04-01 07:57:21 -05:00
  • 157cde914b removing MIME section Francisco Javier Arceo 2025-04-01 08:11:34 -04:00
  • 29b9e819af fix _client in embedding raspawar 2025-04-01 11:04:54 +00:00
  • ca2c46a6e3
    Update llama_stack/distribution/server/server.py Peter Double 2025-04-01 05:29:30 -04:00
  • b7072c3c67
    Update llama_stack/distribution/server/server.py Peter Double 2025-04-01 05:29:14 -04:00
  • ac0ef1a2db docs: Updating contribution docs to source README.md directly Francisco Javier Arceo 2025-04-01 00:42:29 -04:00
  • 696bcf6051
    Merge branch 'meta-llama:main' into add-unit-tests-and-fix-cli Courtney Pacheco 2025-03-31 21:17:48 -04:00
  • 15cf0e0b32 fix: mention PaginatedResponse in api generator error when list returned Ihar Hrachyshka 2025-03-31 19:12:55 -04:00
  • 84d8f9056c fix: add more explicit prescriptions to api validator methods Ihar Hrachyshka 2025-03-31 09:51:38 -04:00
  • 508381a81d fix(api): don't return list for runtime tools Ihar Hrachyshka 2025-03-18 18:22:48 -04:00
  • 014e3ad280
    fix: increase integration test timeout Sébastien Han 2025-03-31 22:12:07 +02:00
  • 5da4839c5a
    single quotes Ashwin Bharambe 2025-03-21 08:35:06 -07:00
  • cfdb8adf36
    if conditional Ashwin Bharambe 2025-03-21 08:34:08 -07:00
  • b3e5b8b4d0
    another Ashwin Bharambe 2025-03-21 08:32:27 -07:00
  • fe971dbd6c
    quotes Ashwin Bharambe 2025-03-21 08:29:10 -07:00
  • 968c9a8346
    matrixify Ashwin Bharambe 2025-03-21 07:19:27 -07:00
  • e483004d82
    add agents Ashwin Bharambe 2025-03-21 06:30:34 -07:00
  • 7ce1a4a80a
    test: make sure integration tests runs against the server Ashwin Bharambe 2025-03-21 06:27:38 -07:00
  • 8e15e3c1b8
    refactor: extract pagination logic into shared helper function Sébastien Han 2025-03-24 17:49:19 +01:00
  • 0f6dc78789 docs: Update readme for integration tests Francisco Javier Arceo 2025-03-31 15:26:41 -04:00
  • e71a482d71 requirements.txt to match main Peter Double 2025-03-31 14:59:59 -04:00
  • c804173902
    Update docs/source/getting_started/index.md raghotham 2025-03-31 11:41:10 -07:00
  • b16fb5a92e
    Update docs/source/getting_started/index.md raghotham 2025-03-31 11:40:31 -07:00
  • 2847216efb docs: Updated documentation and configuration to make things easier for the unfamiliar Francisco Javier Arceo 2025-03-31 13:08:22 -04:00
  • 0194f8783a docs: Adding darkmode to documentation Francisco Javier Arceo 2025-03-31 09:41:44 -04:00
  • ec9a319034
    Updated server.py Peter Double 2025-03-30 18:17:27 -04:00
  • 3d4e81641f
    Update requirements.txt Peter Double 2025-03-30 13:31:47 -04:00
  • de60fb571f fix: FastAPI built-in paths bypass custom routing (Docs) and update requirements document Peter Double 2025-03-30 11:12:35 -04:00
  • 17d9f60ea2 precommit Xi Yan 2025-03-29 12:05:21 -07:00
  • 21c185403a work with all types Xi Yan 2025-03-29 12:02:14 -07:00
  • e84d3966c4 change context to content Xi Yan 2025-03-29 11:55:50 -07:00
  • 77cac70dd3
    Simplify getting started doc raghotham 2025-03-29 11:40:45 -07:00
  • bbf3fa8e1c
    docs: Add link to integration tests instructions and minor clarification Yuan Tang 2025-03-29 14:21:23 -04:00
  • 0492317099
    fix: update sink name for traces and metrics in LlamaStack 0.1.8 AIMikav 2025-03-29 13:02:46 +00:00
  • 7f0ace11f2 skip prompting for an api provider if none exists Matthew Farrellee 2025-03-29 07:46:53 -04:00
  • 820c04ae48 fix(telemetry): library client does not log span Eric Huang 2025-03-28 23:45:01 -07:00
  • 650cbc395d dropped impls for hf serverless and hf endpoint Hardik Shah 2025-03-28 22:38:16 -07:00
  • 1b15df8d1d drop hf serverless and endpoint Hardik Shah 2025-03-28 22:18:40 -07:00
  • 5251d2422d fixes and linting Hardik Shah 2025-03-28 18:33:36 -07:00
  • fe090ce14d fix(telemetry): query_spans Eric Huang 2025-03-28 20:42:15 -07:00
  • ad9b8da796 chore: Updating Milvus Client calls to be non-blocking Francisco Javier Arceo 2025-03-28 21:39:29 -04:00
  • 337aa6d183 build: Bump version to 0.1.9 v0.1.9 release-0.1.9 github-actions[bot] 2025-03-29 00:22:07 +00:00
  • 54747c28fc Release candidate 0.1.19rc8 v0.1.19rc8 github-actions[bot] 2025-03-28 23:53:32 +00:00
  • 021dd0d35d make TGI work well Hardik Shah 2025-03-28 15:38:27 -07:00
  • e74e0ca5a6 fix(telemetry): root span not yet received Eric Huang 2025-03-28 14:31:15 -07:00
  • c43d8bbec7 skip code interp Xi Yan 2025-03-28 12:50:32 -07:00
  • 876693e710 skip code interp Xi Yan 2025-03-28 12:48:56 -07:00
  • 6c779eef2c fix: Adding chunk_size_in_tokens to playground rag_tool insert Francisco Javier Arceo 2025-03-28 15:33:25 -04:00
  • 41dbb91371
    Update readme for v1.8 Yu An 2025-03-28 18:48:47 +00:00
  • 2433ef218d feat: implement async job scheduler for torchtune Ihar Hrachyshka 2025-03-05 19:37:32 -05:00
  • 71561cb63b
    ci: add myself to CODEOWNERS Sébastien Han 2025-03-28 17:01:05 +01:00
  • 6434cdfdab fix: Run prompt_guard model in a seperate thread Derek Higgins 2025-03-21 14:22:33 +00:00
  • 02408dc2da adjusting table Francisco Javier Arceo 2025-03-28 09:21:06 -04:00
  • 9a014b2822 updating based on feedback Francisco Javier Arceo 2025-03-28 09:19:14 -04:00
  • 1ac05d3a2a updated copy and cleaned up files Francisco Javier Arceo 2025-03-27 21:58:57 -04:00