Commit graph

  • a6ddbae0ed
    chore(test): migrate unit tests from unittest to pytest nvidia test eval (#3249) Mustafa Elbehery 2025-11-04 10:29:07 +01:00
  • 357be98279
    wip2 Sébastien Han 2025-10-31 12:03:39 +01:00
  • 38de8ea1f7
    wip Sébastien Han 2025-10-30 17:56:42 +01:00
  • 5fe73c5ecd chore(test): migrate unit tests from unittest to pytest nvidia test eval Mustafa Elbehery 2025-07-17 10:57:04 +02:00
  • ec702ac3fb
    wip Sébastien Han 2025-10-30 17:56:42 +01:00
  • a019d0e02a
    chore: use Pydantic to generate OpenAPI schema Sébastien Han 2025-10-29 14:38:56 +01:00
  • 2d52334a6c docs: Add Llama Stack Operator docs Vaishnavi Hire 2025-10-30 13:14:02 -04:00
  • 9885c522c3
    Merge 2367a4ff80 into sapling-pr-archive-ehhuang ehhuang 2025-11-03 21:25:26 -08:00
  • 2367a4ff80 v0 pr4057 Eric Huang 2025-11-03 21:17:51 -08:00
  • b5690f98e5 precommit Ashwin Bharambe 2025-11-03 20:24:50 -08:00
  • 4c7163d021 clean up unused imports after agents API removal Ashwin Bharambe 2025-11-03 20:11:19 -08:00
  • 642691ed4c chore!: remove the agents (sessions and turns) API Ashwin Bharambe 2025-11-03 20:05:33 -08:00
  • 9dbeeaca97 Removed the MCPAuthorization class relying on bearer token Omar Abdelwahab 2025-11-03 19:57:58 -08:00
  • 053fc0ac39
    chore!: remove all deprecated routes (including /openai/v1/ ones) (#4054) Ashwin Bharambe 2025-11-03 19:00:59 -08:00
  • aaf97f6546 pre-commit Ashwin Bharambe 2025-11-03 18:45:40 -08:00
  • 93e9df219e chore: remove all deprecated=True route decorators Ashwin Bharambe 2025-11-03 18:44:37 -08:00
  • a0979f24c8 fix the models endpoint Ashwin Bharambe 2025-11-03 17:54:51 -08:00
  • 1b9c2fc15e chore: remove deprecated /openai/v1/ routes Ashwin Bharambe 2025-11-03 17:45:45 -08:00
  • 7cd3cd1213
    Merge branch 'main' into add-mongodb-vector_io Young Han 2025-11-03 17:39:53 -08:00
  • b728307427
    Merge branch 'main' into feat/gunicorn-production-server Ashwin Bharambe 2025-11-03 17:39:30 -08:00
  • 62b3ad349a
    fix: return to hardcoded model IDs for Vertex AI (#4041) Nathan Weinberg 2025-11-03 20:38:16 -05:00
  • cb40da210f
    fix: update tests for OpenAI-style models endpoint (#4053) Ashwin Bharambe 2025-11-03 17:30:08 -08:00
  • 23b10c58c6 precommit Ashwin Bharambe 2025-11-03 17:29:50 -08:00
  • d0064fc915
    Merge branch 'main' into add-mongodb-vector_io Young Han 2025-11-03 17:27:31 -08:00
  • dcca50e125 fix: update UI and docs to use OpenAI-style model response fields Ashwin Bharambe 2025-11-03 17:22:36 -08:00
  • b34c928d43 chore: update distribution templates with MongoDB connection parameters Young Han 2025-11-03 17:18:33 -08:00
  • 376f0fcd23 minor fix Omar Abdelwahab 2025-11-03 17:02:30 -08:00
  • 83276d4aaa fix(mongodb): update protocol compliance and add graceful connection failure handling Young Han 2025-11-03 17:01:25 -08:00
  • 1143db0f64 added a fix Omar Abdelwahab 2025-11-03 16:55:13 -08:00
  • 809dae01c2 fix: update tests for OpenAI-style models endpoint Ashwin Bharambe 2025-11-03 16:16:16 -08:00
  • 59468f2c5d fix: return to hardcoded model IDs for Vertex AI Nathan Weinberg 2025-11-03 10:05:50 -05:00
  • 715d4f8d8c test pr4056 Eric Huang 2025-11-03 16:16:02 -08:00
  • c49fef8087 precommit Omar Abdelwahab 2025-11-03 16:12:38 -08:00
  • 4a5ef65286
    chore!: remove SDG API (#4035) Sébastien Han 2025-11-04 01:12:06 +01:00
  • 551b91b3e7
    Merge branch 'main' into rm-sdg Ashwin Bharambe 2025-11-03 16:04:41 -08:00
  • c4ee3dcb35 fix(mongodb): rename vector_db parameters to vector_store for OpenAI Vector Stores mixin compatibility Young Han 2025-11-03 15:58:52 -08:00
  • 57eb575ea1 Added minor changes Omar Abdelwahab 2025-11-03 15:57:45 -08:00
  • 44096512b5
    feat: add custom_metadata to OpenAIModel to unify /v1/models with /v1/openai/v1/models (#4051) Ashwin Bharambe 2025-11-03 15:56:07 -08:00
  • d0a8878337 MCP authentication parameter implementation Omar Abdelwahab 2025-11-03 15:48:56 -08:00
  • ed79d69e43 we need to make openai/v1/models non deprecated so we can include in stainless Ashwin Bharambe 2025-11-03 15:38:56 -08:00
  • bb51cb3ba7 precomit Ashwin Bharambe 2025-11-03 15:31:47 -08:00
  • 2381714904
    fix: enable SQLite WAL mode to prevent database locking errors (#4048) Ashwin Bharambe 2025-11-03 15:27:41 -08:00
  • 628e38b3d5
    test: always start a new server in integration-tests.sh (#4050) ehhuang 2025-11-03 15:23:10 -08:00
  • 3f79df2faa fix: remove flush() call and disable write queues for SQLite to prevent deadlock Ashwin Bharambe 2025-11-03 15:21:46 -08:00
  • c280b22d13 ran precommit Omar Abdelwahab 2025-11-03 15:14:42 -08:00
  • 3af73b754a feat: add custom_metadata to OpenAIModel to unify /v1/models with /v1/openai/v1/models Ashwin Bharambe 2025-11-03 15:11:58 -08:00
  • 4d09b713ac
    Merge b0eb9eb05a into sapling-pr-archive-ehhuang ehhuang 2025-11-03 15:11:48 -08:00
  • b0eb9eb05a test: port Eric Huang 2025-11-03 15:11:43 -08:00
  • 20654671e2 added a minor change Omar Abdelwahab 2025-11-03 15:10:32 -08:00
  • cd87a5d439 merge commit for archive created by Sapling Eric Huang 2025-11-03 15:08:28 -08:00
  • 7c669ef65f test: port Eric Huang 2025-11-03 15:08:20 -08:00
  • dd11b28a3c merge commit for archive created by Sapling Eric Huang 2025-11-03 15:06:05 -08:00
  • bacde5f9d1 test: port Eric Huang 2025-11-03 15:02:35 -08:00
  • 6c57445139 Added a fix for issue number 4034 Omar Abdelwahab 2025-11-03 14:55:34 -08:00
  • 09f38c9ce6 pre commit ugh Ashwin Bharambe 2025-11-03 14:48:28 -08:00
  • 554d958931 fix: keep write queues enabled, flush before returning non-streaming responses Ashwin Bharambe 2025-11-03 14:34:23 -08:00
  • a63e0a84d3 fix: disable write queue for SQLite, let WAL handle concurrency Ashwin Bharambe 2025-11-03 14:27:15 -08:00
  • b74752dd54 fix: add missing enable_write_queue initialization in InferenceStore Ashwin Bharambe 2025-11-03 14:23:23 -08:00
  • 168c1209a0 fix: enable SQLite WAL mode to prevent database locking errors Ashwin Bharambe 2025-11-03 14:19:01 -08:00
  • da57b51fb6
    ci: introduce Mergify bot to notify on PR conflicts (#4043) Sébastien Han 2025-11-03 21:21:19 +01:00
  • 8a1cd117cc
    Merge branch 'main' into use-json-schema Ashwin Bharambe 2025-11-03 12:20:28 -08:00
  • 1562277cfd
    ci: test adjustments for Qwen3-0.6B (#3978) Derek Higgins 2025-11-03 20:19:35 +00:00
  • 493e9c5c5b
    Merge branch 'main' into qwen-clue Ashwin Bharambe 2025-11-03 12:12:54 -08:00
  • 1263448de2
    fix: allowed_models config did not filter models (#4030) Matthew Farrellee 2025-11-03 14:43:39 -05:00
  • cf7436c167
    Merge branch 'main' into issue-4022 Ashwin Bharambe 2025-11-03 11:38:48 -08:00
  • 30f8921240
    fix: generate provider config when using --providers (#4044) Charlie Doern 2025-11-03 14:37:58 -05:00
  • 202a28f8ca
    Merge 7a19488787 into sapling-pr-archive-ehhuang ehhuang 2025-11-03 10:46:12 -08:00
  • 7a19488787 metrics tests pr4045 Emilio Garcia 2025-11-03 10:45:30 -08:00
  • 9b8240e740 remove MagicMock for argparse.Namespace Charlie Doern 2025-11-03 11:30:20 -05:00
  • 4336bf96a5 Merge remote-tracking branch 'origin/main' into fix-providers Ashwin Bharambe 2025-11-03 09:49:46 -08:00
  • 415fd9e36b
    chore: bump version to 0.4.0.dev0 (#4018) Ashwin Bharambe 2025-11-03 09:36:04 -08:00
  • ecc62dd51d update uv lock Ashwin Bharambe 2025-11-03 09:28:50 -08:00
  • 8f7a7d81f3
    chore!: remove SDG API Sébastien Han 2025-11-03 11:24:45 +01:00
  • 7ecd015b41
    chore: remove yq install on CI Sébastien Han 2025-11-03 12:16:40 +01:00
  • 0671189e34
    chore: add backward compatibility in CI Sébastien Han 2025-11-03 12:06:52 +01:00
  • 44e36ce48d
    chore: use JSON instead of YAML for openapi generation Sébastien Han 2025-11-03 11:54:50 +01:00
  • d4aa348b60
    chore: remove HTML generation for openapi spec (#4039) Sébastien Han 2025-11-03 18:03:40 +01:00
  • 23b8535022 fix: generate provider config when using --providers Charlie Doern 2025-11-03 11:30:20 -05:00
  • 21f4648c7f
    ci: introduce Mergify bot to notify on PR conflicts Sébastien Han 2025-03-17 15:53:53 +01:00
  • 7e294d33d9
    chore(github-deps): bump astral-sh/setup-uv from 6.0.1 to 7.1.2 (#4023) dependabot[bot] 2025-11-03 13:43:04 +01:00
  • 28edebc333
    chore: remove llama-stack-spec.html mention Sébastien Han 2025-11-03 12:17:43 +01:00
  • 3aa006322c
    chore: remove HTML generation for openapi spec Sébastien Han 2025-11-03 12:02:26 +01:00
  • 3dbff6bf3f
    fix: help mypy & fix precommit on main (#4037) Sébastien Han 2025-11-03 11:39:50 +01:00
  • 4928048d73
    fix: help mypy & fix precommit on main Sébastien Han 2025-11-03 11:28:25 +01:00
  • 650d2fd9e3 fix: show built-in distributions in llama stack list Roy Belio 2025-11-03 12:23:07 +02:00
  • 47bd994824
    Merge branch 'main' into feat/gunicorn-production-server Roy Belio 2025-11-02 16:13:15 +02:00
  • 5fd4e52b01
    Update docs/docs/distributions/starting_llama_stack_server.mdx Roy Belio 2025-11-02 16:11:10 +02:00
  • 2f2c7f4305
    Update docs/docs/distributions/self_hosted_distro/starter.md Roy Belio 2025-11-02 16:11:02 +02:00
  • 4a75f10758
    Update src/llama_stack/cli/stack/run.py Roy Belio 2025-11-02 16:10:52 +02:00
  • 84f0418194 fix: allowed_models config did not filter models Matthew Farrellee 2025-11-02 07:00:39 -05:00
  • 321f99fe09 Add dana agent provider stub zooeyn 2025-11-01 18:29:43 -07:00
  • 92acb4fc21
    chore(python-deps): bump tiktoken from 0.9.0 to 0.12.0 dependabot[bot] 2025-11-01 20:05:38 +00:00
  • 09872fc6c6
    chore(python-deps): bump aiohttp from 3.12.14 to 3.13.2 dependabot[bot] 2025-11-01 20:05:32 +00:00
  • a63e923254
    chore(python-deps): bump locust from 2.40.1 to 2.42.1 dependabot[bot] 2025-11-01 20:05:12 +00:00
  • c5808ee38a
    chore(python-deps): bump pymilvus from 2.6.1 to 2.6.3 dependabot[bot] 2025-11-01 20:05:05 +00:00
  • 3c61e89c4e
    chore(python-deps): bump torch from 2.8.0 to 2.9.0 dependabot[bot] 2025-11-01 20:04:59 +00:00
  • 6d472778fb
    chore(github-deps): bump astral-sh/setup-uv from 6.0.1 to 7.1.2 dependabot[bot] 2025-11-01 20:04:29 +00:00
  • d45137a399
    fix(ci): export UV_INDEX_STRATEGY to current shell before running uv sync (#4020) Ashwin Bharambe 2025-11-01 12:57:24 -07:00
  • 8b878e9d48
    fix(ci): export UV_INDEX_STRATEGY to current shell before running uv sync (#4019) Ashwin Bharambe 2025-11-01 12:54:19 -07:00
  • 49ea24e8fd Update UI package-lock.json to sync with package.json Ashwin Bharambe 2025-11-01 12:50:29 -07:00