Commit graph

  • d843672482 ci(installer): end-to-end smoke test and scheduled health check reluctantfuturist 2025-04-17 15:45:14 -07:00
  • 9edda486ae feat(installer): add Podman support, bump default model to 3b, document internal DNS reluctantfuturist 2025-04-17 11:37:44 -07:00
  • e70c4e67de refactor(install): simplify demo to two‑container flow, drop host‑level installs reluctantfuturist 2025-04-16 12:05:58 -07:00
  • 6d5d1480c9 ollama distro install reluctantfuturist 2025-03-04 20:46:35 -08:00
  • 6d4a4438ac feat(install): add Llama Stack Meta Reference installation script reluctantfuturist 2025-03-03 22:47:16 -08:00
  • 92142fe0cd
    Maded changes on streamlit with ReAct agent mode Andy Xie 2025-04-24 02:01:09 -04:00
  • 74bacbe77b
    fixed precommit check Roland Huß 2025-04-25 15:40:30 +02:00
  • c71006f9cc
    chore: exclude test, provider, and template directories from coverage Sébastien Han 2025-04-25 14:14:29 +02:00
  • 8f701a831d
    feat(cli): add interactive tab completion for image type selection Roland Huß 2025-04-25 13:55:59 +02:00
  • ec4c04fa2d docs: Fix missing --gpu all flag in Docker run commands Derek Higgins 2025-04-25 12:06:08 +01:00
  • 7397534497 docs: Remove docs for meta-reference-quantized-gpu Derek Higgins 2025-04-25 12:33:06 +01:00
  • 2f498ad776 updated the string to watsonx Sajikumar JS 2025-04-25 11:03:21 +05:30
  • 6fe8b292b1 Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-25 10:57:45 +05:30
  • 26c10b5ab5 fix: Correctly parse algorithm_config when launching NVIDIA customization job Jash Gulabrai 2025-04-24 17:17:00 -04:00
  • f557e16d0c Enhance tool display in Tools sidebar by simplifying tool identifiers Surya Prakash Pathak 2025-04-24 13:26:40 -07:00
  • 9d05aff960 specify nbformat version in nb Kevin 2025-04-24 15:51:07 -04:00
  • 9b58624479 fixes Eric Huang 2025-04-24 12:08:11 -07:00
  • 693c709c27 fixes Eric Huang 2025-04-24 12:03:55 -07:00
  • a452c64300 docs: Add TrustyAI LM-Eval to list of known external providers Christina Xu 2025-04-24 14:45:48 -04:00
  • 0990f60dad Merge branch 'main' of https://github.com/meta-llama/llama-stack into register_custom_model raspawar 2025-04-24 21:44:32 +05:30
  • 516f8dffb4 chore: Remove distributions/** from integration, external provider, and unit tests Francisco Javier Arceo 2025-04-24 11:31:42 -04:00
  • 8d7225507f removing integration tests Francisco Javier Arceo 2025-04-24 11:02:54 -04:00
  • e24959ea9e Fix variable name Jash Gulabrai 2025-04-24 10:41:38 -04:00
  • edbf85366d adding workflow changes as well Francisco Javier Arceo 2025-04-24 09:35:26 -04:00
  • 2f91b73bcb
    feat(pre-commit): enhance pre-commit hooks with additional checks Sébastien Han 2025-04-24 14:54:04 +02:00
  • f7257e33dc removing integration-tests Francisco Javier Arceo 2025-04-24 08:57:53 -04:00
  • bcc77f829c swapping to paths instead of paths-ignore to be consistent with the integragtion and unit tests Francisco Javier Arceo 2025-04-24 08:56:55 -04:00
  • 4ac7ead646 remove extra space Francisco Javier Arceo 2025-04-24 08:01:32 -04:00
  • 294e91724a
    fix: do not override the entrypoint when running container Sébastien Han 2025-04-24 13:56:08 +02:00
  • a487b0b902
    feat: include run.yaml in the container image Sébastien Han 2025-04-23 11:04:29 +02:00
  • 803b836323 chore: Update External Providers CI to not run on changes to docs, rfcs, and scripts Francisco Javier Arceo 2025-04-23 22:24:57 -04:00
  • 050d4b8cc9 chore: rename ramalama provider Charlie Doern 2025-04-23 15:34:46 -04:00
  • cfa4b61a01 fix: Additional streaming error handling Ben Browning 2025-04-23 13:04:16 -04:00
  • 11810c9a03
    Merge branch 'meta-llama:main' into main Vaishnavi Hire 2025-04-23 11:37:53 -04:00
  • e9ee8eb812 feat: add tool name to chat output Michael Clifford 2025-04-18 15:10:03 -04:00
  • 52f465e967 docs: add API to external providers table Nathan Weinberg 2025-04-23 09:45:16 -04:00
  • af5d0b4c16 docs: add RamaLama to list of known external providers Nathan Weinberg 2025-04-22 14:51:25 -04:00
  • cf42b6f801 Playground UI: hide tool output under an expander widget. ilya-kolchinsky 2025-04-22 17:49:48 +02:00
  • 6fe64ee169 Including tool call in chat Derek Higgins 2025-04-10 13:20:09 +00:00
  • 922ac2d501 address disagreement between ruff versions Matthew Farrellee 2025-04-22 10:00:46 -04:00
  • 519afdde5f vllm unit test, check for exception on error Matthew Farrellee 2025-04-22 09:54:57 -04:00
  • c436269cd4 update ollama register_model to follow aliases Matthew Farrellee 2025-04-22 09:35:08 -04:00
  • 84351c2d67 flatten alias to provider map, test registering to existing alias Matthew Farrellee 2025-04-22 09:33:06 -04:00
  • 9982aa64f0 fix: allow lookup of models registered at runtime Matthew Farrellee 2025-04-16 15:51:08 -04:00
  • 43d4b7527b fix: Return HTTP 400 for OpenAI API validation errors Ben Browning 2025-04-21 22:07:04 -04:00
  • 544a804678 fix: Together provider shutdown and default to non-streaming Ben Browning 2025-04-21 17:06:44 -04:00
  • 45ef6eac10 fix: properly handle streaming client disconnects Ben Browning 2025-04-21 16:10:45 -04:00
  • 3e2c418524 RFC: Configuring search modes for RAG Varsha Prasad Narsing 2025-04-11 12:50:25 -07:00
  • 9a1b93abb5 Update NVIDIA to GA docs; remove notebook reference until ready Jash Gulabrai 2025-04-18 17:01:51 -04:00
  • 8fd656dcac Add changes Jash Gulabrai 2025-04-18 16:28:04 -04:00
  • 4131e8146f Clean up instructions and implementation; reorganize notebooks Jash Gulabrai 2025-04-18 16:27:19 -04:00
  • 4ee828a277 feat: cleanup sidebar formatting on tools playground Michael Clifford 2025-04-18 16:15:20 -04:00
  • 1dcde0de67 fix: OpenAI Completions API and Fireworks Ben Browning 2025-04-18 15:57:02 -04:00
  • 909fc692ce add examples for how to define RAG docs Kevin 2025-04-16 21:39:37 -04:00
  • c9a41288a3 feat: RamaLama Documentation and Templates Daniel J Walsh 2025-02-11 13:47:13 -05:00
  • 4de45560bf feat: remote ramalama provider implementation Charlie Doern 2025-03-11 18:15:45 -04:00
  • 89dbf91323
    feat: allow building distro with external providers Sébastien Han 2025-04-16 13:04:43 +02:00
  • c66245b4e7 update ref to raw_errors due to new version of pydantic Kevin 2025-04-18 10:19:17 -04:00
  • a2b7075fe9
    More specific guidance Yuan Tang 2025-04-18 08:30:41 -04:00
  • 2b1620f8d8
    regenerate Yuan Tang 2025-04-17 20:29:52 -04:00
  • ca43978809
    docs: Add tips for debugging remote vLLM provider Yuan Tang 2025-04-17 20:28:24 -04:00
  • 4b1aa2987f
    fix: Fix docs lint issues Yuan Tang 2025-04-17 20:33:04 -04:00
  • d4ec593a35 docs(build): clarify UBI9 compiler requirement and remove redundant test reluctantfuturist 2025-04-17 17:02:36 -07:00
  • 220da33402 add todo for schema validation Kevin 2025-04-17 19:35:06 -04:00
  • c4b754c9b2 tests: add multi_image test Eric Huang 2025-04-17 12:22:55 -07:00
  • 36de927fd6 add check for interleavedContent Kevin 2025-04-16 15:47:22 -04:00
  • d5abe2ec2e tests: add multi_image test Eric Huang 2025-04-17 11:38:32 -07:00
  • c407f3c340 Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-17 23:45:57 +05:30
  • efe5b124f3 pre-commit issues fix Sajikumar JS 2025-04-17 23:45:27 +05:30
  • 8e0217c7bf Fix reverted change to distro_type Jash Gulabrai 2025-04-17 14:14:12 -04:00
  • c171fc6062 fix: OAI compat endpoint for meta reference inference provider Eric Huang 2025-04-17 11:10:09 -07:00
  • 9303fa61c5 Remove file that was removed Jash Gulabrai 2025-04-17 14:03:28 -04:00
  • 397651b69e Merge branch 'main' into nvidia-eval-integration Jash Gulabrai 2025-04-17 14:02:55 -04:00
  • 92aac3ec4d Add back file that was removed Jash Gulabrai 2025-04-17 14:01:05 -04:00
  • 2117af25a7 Merge branch 'main' into nvidia-eval-integration Jash Gulabrai 2025-04-17 13:36:42 -04:00
  • c996ca6a64 chore(verification): update README and reorganize generate_report.py Eric Huang 2025-04-17 10:27:46 -07:00
  • 26393e2186 update nvidia inference provider to use model_store Matthew Farrellee 2025-04-17 10:43:39 -04:00
  • ceecd1c3e6
    fix: resync api spec Sébastien Han 2025-04-17 17:34:10 +02:00
  • bb4ff1dd1f update nvidia inference provider to use model_store Matthew Farrellee 2025-04-17 10:43:39 -04:00
  • bfc960a691 Fallback to provided model in run_eval Jash Gulabrai 2025-04-17 10:39:09 -04:00
  • 0d9d333a4e Ensure sampling_params param is included in run_eval calls Jash Gulabrai 2025-04-17 10:23:21 -04:00
  • 120987f9e1
    Update llama_stack/apis/agents/agents.py raghotham 2025-04-17 07:02:12 -07:00
  • e466962e11 add meta/llama-3.3-70b-instruct as supported nvidia inference provider model Matthew Farrellee 2025-04-17 09:08:57 -04:00
  • 6c77d7f693 Add link to public docs Jash Gulabrai 2025-04-17 08:44:21 -04:00
  • a5ab39a497 fix: add missing openai_ methods Philippe Martin 2025-04-17 11:53:22 +02:00
  • 6f77ca1755
    Update llama_stack/providers/remote/inference/vllm/vllm.py Ilya Kolchinsky 2025-04-17 11:35:41 +02:00
  • cfc68012f7 fix: use model-id Jeff MAURY 2025-04-03 19:06:17 +02:00
  • 0397c0cd44 fix: telemetry configuration Jeff MAURY 2025-03-26 18:16:33 +01:00
  • aa68e98b7a fix: rewording Jeff MAURY 2025-03-26 15:51:05 +01:00
  • dd86427ce3 feat: Podman AI Lab provider and distribution Jeff MAURY 2025-03-20 16:09:15 +01:00
  • 64d8cde4a0
    fix: print traceback on build failure Sébastien Han 2025-04-16 13:10:17 +02:00
  • 0de530e99f chore: revert CI workflow YAMLs to main versions reluctantfuturist 2025-04-17 00:10:26 -07:00
  • bbbff4309b test fix reluctantfuturist 2025-04-17 00:02:59 -07:00
  • 2396b1e13a fix(build): add UBI 9 compiler tool‑chain and split fast/slow tests (#1970) reluctantfuturist 2025-04-16 23:34:29 -07:00
  • 34a3f1a749 Merge branch 'main' into add-watsonx-inference-adapter Sajikumar JS 2025-04-17 10:43:38 +05:30
  • 48567ebfa3 fix(build): always pass build file path when no template/config is provided reluctantfuturist 2025-04-16 22:11:16 -07:00
  • 88aa70add7 Remove remote_hosted_distro nvidia doc Jash Gulabrai 2025-04-16 18:46:26 -04:00
  • 138cff00b8 test: fix dataset Eric Huang 2025-04-16 15:19:55 -07:00
  • 7fd247b65a Change distro type to self_hosted Jash Gulabrai 2025-04-16 18:21:41 -04:00
  • 94614b26c3 Add docs for Inference and Safety Jash Gulabrai 2025-04-16 18:18:29 -04:00