Commit graph

  • b79e0435de
    fix: avoid tensor memory error (#1688) yyymeta 2025-03-18 16:17:29 -07:00
  • 9c8e88ea9c
    fix: Fixed import errors for UI and playground (#1666) Sarthak Deshpande 2025-03-19 03:30:48 +05:30
  • 0cbb7f7f21
    chore: fix mypy violations in post_training modules (#1548) Ihar Hrachyshka 2025-03-18 17:58:16 -04:00
  • f86f3cf878
    docs: remove redundant installation instructions (#1138) Sébastien Han 2025-03-18 22:52:21 +01:00
  • 22e560351e
    ci: Add scheduled workflow to update changelog (#1503) Yuan Tang 2025-03-18 17:39:22 -04:00
  • 5ece262976
    chore: Make code interpreter async (#1654) Sarthak Deshpande 2025-03-19 02:43:46 +05:30
  • d609ffce2a
    chore: Add links and badges to both unit and integration tests (#1632) Yuan Tang 2025-03-18 17:12:17 -04:00
  • c029fbcd13
    fix: return 4xx for non-existent resources in GET requests (#1635) Sébastien Han 2025-03-18 22:06:53 +01:00
  • cca9bd6cc3
    feat: Qdrant inline provider (#1273) Daniele Martinoli 2025-03-18 22:04:21 +01:00
  • 141b3c14dd
    docs: fix broken test path in CONTRIBUTING.md (#1679) Nathan Weinberg 2025-03-18 16:39:46 -04:00
  • 814eb75321
    chore: enable ruff for ./scripts too (#1643) Ihar Hrachyshka 2025-03-18 15:17:21 -04:00
  • 706b4ca651
    feat: support nvidia hosted vision models (llama 3.2 11b/90b) (#1278) Matthew Farrellee 2025-03-18 13:54:10 -05:00
  • f4dc290705
    feat: Created Playground Containerfile and Image Workflow (#1256) Jamie Land 2025-03-18 12:26:49 -04:00
  • ffe9b3b278
    ci(ollama): run more integration tests (#1636) Sébastien Han 2025-03-18 16:54:42 +01:00
  • 168cbcbb92
    fix: Add the option to not verify SSL at remote-vllm provider (#1585) Luis Tomas Bolivar 2025-03-18 14:33:35 +01:00
  • 37f155e41d
    feat(agent): support multiple tool groups (#1556) ehhuang 2025-03-17 22:13:09 -07:00
  • c23a7af5d6
    fix: agents with non-llama model (#1550) ehhuang 2025-03-17 22:11:06 -07:00
  • 0bdfc71f8d
    test: Bump slow_callback_duration to 200ms to avoid flaky remote vLLM unit tests (#1675) Yuan Tang 2025-03-18 00:33:04 -04:00
  • 2d2bb701fa
    ci: Add dependabot scans for Python deps (#1618) Yuan Tang 2025-03-17 23:20:31 -04:00
  • e14f69eb7e
    chore: Remove unused cursor rules (#1653) Yuan Tang 2025-03-17 23:19:37 -04:00
  • 1261bc93bf
    docs: fixed broken tip in distro build docs (#1673) Nathan Weinberg 2025-03-17 20:22:26 -04:00
  • 5287b437ae
    feat(api): (1/n) datasets api clean up (#1573) Xi Yan 2025-03-17 16:55:45 -07:00
  • 3b35a39b8b
    ci: limit PR testing based on modified files (#1644) Nathan Weinberg 2025-03-17 18:20:29 -04:00
  • 24fd06879e
    refactor: simplify command execution and remove PTY handling (#1641) Sébastien Han 2025-03-17 23:03:14 +01:00
  • 77ca09467f
    chore: consolidate scripts under ./scripts directory (#1646) Ihar Hrachyshka 2025-03-17 17:56:30 -04:00
  • e48af78b76
    fix: add shutdown method for ProviderImpl (#1670) Nathan Weinberg 2025-03-17 17:55:40 -04:00
  • 252a487085
    feat: added nvidia as safety provider (#1248) cdgamarose-nv 2025-03-17 14:39:23 -07:00
  • ac51564ad5
    docs: Fixing outputs in client cli and formatting suggestions (#1668) Kelly Brown 2025-03-17 17:31:09 -04:00
  • f11b6db40d
    fix: build distribution with podman (#1671) Jeff MAURY 2025-03-17 22:30:06 +01:00
  • dfa11a1216
    fix: fixed import error (#1637) Sarthak Deshpande 2025-03-18 02:34:47 +05:30
  • fb418813fc
    fix: passthrough impl response.content.text (#1665) yyymeta 2025-03-17 13:42:08 -07:00
  • 60ae7455f6
    docs: Fix trailing whitespace error (#1669) Kelly Brown 2025-03-17 11:53:30 -04:00
  • b56b06037c
    Web updates to point to latest releases for Mobile SDK (#1650) Chirag Modi 2025-03-14 17:06:07 -07:00
  • d2dda4af64
    docs: add additional guidance around using virtualenv (#1642) Nathan Weinberg 2025-03-14 19:00:55 -04:00
  • 7b81761a56 fix: update CDN url for stoplight Ashwin Bharambe 2025-03-14 15:46:45 -07:00
  • 93cfade8c9 ci: Bump version to 0.1.7 Ashwin Bharambe 2025-03-14 15:21:26 -07:00
  • c5857a9b50 fix: sleep between tests oof Ashwin Bharambe 2025-03-14 14:45:37 -07:00
  • a626b7bce3
    feat: [new open benchmark] BFCL_v3 (#1578) yyymeta 2025-03-14 12:50:49 -07:00
  • 78d4872c0c
    feat: add support for logging config in the run.yaml (#1408) Charlie Doern 2025-03-14 15:36:25 -04:00
  • e3e7013ac8
    chore: Add pre-commit check to sync api spec docs (#1609) Ihar Hrachyshka 2025-03-14 12:20:49 -04:00
  • bfc79217a8
    chore: Add ./scripts/unit-tests.sh (#1515) Ihar Hrachyshka 2025-03-13 23:25:15 -04:00
  • 33b096cc21
    fix: OpenAPI with provider get (#1627) Xi Yan 2025-03-13 19:56:32 -07:00
  • 9e73341008
    fix: change dog.jpg path in test_vision_inference.py (#1624) Kai Wu 2025-03-13 18:58:12 -07:00
  • ca0cbf4338
    fix: Fix pre-commit check (#1628) Yuan Tang 2025-03-13 21:57:42 -04:00
  • c02464b635
    fix: Clarify llama model prompt-format help text (#1010) Alina Ryan 2025-03-13 20:47:09 -04:00
  • 98b1b15e0f
    refactor: move all datetime.now() calls to UTC (#1589) Sébastien Han 2025-03-13 23:34:53 +01:00
  • b906bad238
    docs: Add OpenAI, Anthropic, Gemini to inference API providers table (#1622) Yuan Tang 2025-03-13 18:28:52 -04:00
  • a062723d03
    feat: add provider API for listing and inspecting provider info (#1429) Charlie Doern 2025-03-13 18:07:21 -04:00
  • e101d15f12
    build(deps): bump astral-sh/setup-uv from 4 to 5 (#1620) dependabot[bot] 2025-03-13 16:40:15 -04:00
  • a3d710e59c
    chore: Always check that git merge conflict markers are not present (#1610) Ihar Hrachyshka 2025-03-13 16:19:44 -04:00
  • ed841380dc
    test: turn off recordable mock for now (#1616) ehhuang 2025-03-13 13:18:08 -07:00
  • a1bb7c8d82
    docs: Add OpenAI, Anthropic, Gemini to API providers table (#1617) Yuan Tang 2025-03-13 15:47:58 -04:00
  • 28aade9a27
    ci: add GitHub Action to close stale issues and PRs (#1613) Sébastien Han 2025-03-13 20:09:04 +01:00
  • edfcb02a0e
    ci(ollama): add GitHub Actions workflow for integration tests (#1546) Sébastien Han 2025-03-13 20:04:53 +01:00
  • 42788a9d50
    test: re record responses after client sync (#1615) ehhuang 2025-03-13 11:21:10 -07:00
  • 98811cc034
    fix: clean up test imports (#1600) Xi Yan 2025-03-13 11:01:52 -07:00
  • 5e54113b19
    ci: add dynamic CI job to test templates (#1230) Sébastien Han 2025-03-13 18:14:01 +01:00
  • 9617468d13
    fix: passthrough provider template + fix (#1612) Xi Yan 2025-03-13 09:44:26 -07:00
  • d072b5fa0c
    test: add unit test to ensure all config types are instantiable (#1601) Ashwin Bharambe 2025-03-12 22:29:58 -07:00
  • 0a0d6cb96e
    fix: openapi spec gen (#1602) ehhuang 2025-03-12 21:55:05 -07:00
  • d263edbf90
    build: remove .python-version (#1513) Nathan Weinberg 2025-03-12 23:08:24 -04:00
  • a505bf45a3
    feat(api): remove tool_name from ToolResponseMessage (#1599) ehhuang 2025-03-12 19:41:48 -07:00
  • 6bfcb65343
    test: code exec on mac (#1549) ehhuang 2025-03-12 19:21:53 -07:00
  • 2baf200b63
    ci: add html report to unit test artifacts (#1576) Nathan Weinberg 2025-03-12 22:05:49 -04:00
  • ed6caead72
    chore: simplify _get_tool_defs (#1384) ehhuang 2025-03-12 18:51:18 -07:00
  • 41c9bca1aa
    chore: refactor Agent toolgroup processing (#1381) ehhuang 2025-03-12 18:48:03 -07:00
  • 99bbe0e70b
    feat: Add new compact MetricInResponse type (#1593) Dinesh Yeduguru 2025-03-12 15:45:44 -07:00
  • ad939c97c3
    docs: add unit test badge to README (#1591) Nathan Weinberg 2025-03-12 18:41:35 -04:00
  • 1311faf3f5
    fix: logging (#1598) ehhuang 2025-03-12 14:57:31 -07:00
  • 0fdb15bcc7
    fix: fix build error in context.py (#1595) Dinesh Yeduguru 2025-03-12 13:26:23 -07:00
  • b7a9c45477
    chore: deprecate ToolResponseMessage in agent.resume API (#1566) ehhuang 2025-03-12 12:10:21 -07:00
  • 58d08d100e
    feat: Add back inference metrics and preserve context variables across asyncio boundary (#1552) Dinesh Yeduguru 2025-03-12 12:01:03 -07:00
  • c7139b0b67
    fix: fix precommit (#1594) Xi Yan 2025-03-12 11:59:21 -07:00
  • 90ca4d94de
    fix: fix passthrough inference provider to make it work for agent (#1577) Botao Chen 2025-03-12 11:16:17 -07:00
  • 0b0be70605
    feat: Add open benchmark template codegen (#1579) Botao Chen 2025-03-12 11:12:08 -07:00
  • 4eee349acd
    fix: respect log_level in uvicorn and third party libs (#1524) Charlie Doern 2025-03-12 14:07:28 -04:00
  • 00da911167
    ci: run unit tests on all supported python versions (#1575) Nathan Weinberg 2025-03-12 12:55:11 -04:00
  • b1a9b4cfa8
    chore: Expand mypy exclusions list (#1543) Ihar Hrachyshka 2025-03-12 12:53:04 -04:00
  • 59dddafd12
    feat: convert typehints from client_tool to litellm format (#1565) ehhuang 2025-03-11 20:02:11 -07:00
  • 2370e826bc
    test: adding an e2e test for measuring TTFT (#1568) LESSuseLESS 2025-03-11 14:41:55 -07:00
  • 5f90be5388
    fix: Fixed bad file name in inline::localfs (#1358) Josh Salomon 2025-03-11 21:46:11 +02:00
  • 43044f29e2
    fix: fix llama stack run with missing agent impl (#1559) Xi Yan 2025-03-11 11:22:22 -07:00
  • 85501ed875
    fix: remove Llama-3.2-1B-Instruct for fireworks (#1558) Dinesh Yeduguru 2025-03-11 11:19:29 -07:00
  • 275bab1373
    test: loosen Python 3.10 version for unit tests (#1547) Nathan Weinberg 2025-03-11 14:11:32 -04:00
  • b647ecd9ed
    feat: add support for LLAMA_STACK_LOG_FILE (#1450) Charlie Doern 2025-03-11 14:09:31 -04:00
  • 83a2c78615
    feat(api): list agents / sessions and get agent (#1410) Sébastien Han 2025-03-11 18:33:46 +01:00
  • aca82df7ed
    fix: Multiple fixes for server shutdown (fix lifespan handling; fix handling CancelledError when raised by provider; let uvicorn handle signals) (#1495) Ihar Hrachyshka 2025-03-11 13:30:55 -04:00
  • d33b8ea3dc
    docs: Small nits in llama CLI reference (#1542) Kelly Brown 2025-03-11 13:12:18 -04:00
  • c3d7d17bc4
    chore: fix typing hints for get_provider_impl deps arguments (#1544) Ihar Hrachyshka 2025-03-11 13:07:28 -04:00
  • 04106b94aa
    docs: Remove duplicate docs on api docs generator (#1534) Ihar Hrachyshka 2025-03-11 13:01:46 -04:00
  • 0e73186a11
    fix: Add missing shutdown handler for TorchtunePostTrainingImpl (#1535) Ihar Hrachyshka 2025-03-11 13:01:09 -04:00
  • e13c92f269
    revert: feat(server): Use system packages for execution (#1551) Ashwin Bharambe 2025-03-11 09:58:25 -07:00
  • ead9397e22
    fix: tracing fixes for trace context propogation across coroutines (#1522) Dinesh Yeduguru 2025-03-11 07:12:48 -07:00
  • e3edca7739
    feat: [new open benchmark] Math 500 (#1538) Botao Chen 2025-03-10 20:38:28 -07:00
  • ff853ccc38
    fix: Use --with-editable to capture accurate code coverage reporting (#1532) Courtney Pacheco 2025-03-10 19:30:28 -04:00
  • dc84bc755a
    fix: revert to using faiss for ollama distro (#1530) Ashwin Bharambe 2025-03-10 16:15:17 -07:00
  • 21e39633d8
    feat(server): Use system packages for execution (#1252) Sébastien Han 2025-03-11 00:01:03 +01:00
  • feacf89548
    docs: improve integration test doc (#1502) Reid 2025-03-11 06:50:46 +08:00
  • 91b1b92908
    build: revamp "test" dependencies from pyproject (#1468) Sébastien Han 2025-03-10 23:43:16 +01:00
  • 201a7567ef
    test: add inspect unit test (#1417) Sébastien Han 2025-03-10 23:36:18 +01:00