258 commits

Author	SHA1	Message	Date
Akram Ben Aissi	4842145202	feat: Add dynamic authentication token forwarding support for vLLM (#3388) ... # What does this PR do? *Add dynamic authentication token forwarding support for vLLM provider* This enables per-request authentication tokens for vLLM providers, supporting use cases like RAG operations where different requests may need different authentication tokens. The implementation follows the same pattern as other providers like Together AI, Fireworks, and Passthrough. - Add LiteLLMOpenAIMixin that manages the vllm_api_token properly Usage: - Static: VLLM_API_TOKEN env var or config.api_token - Dynamic: X-LlamaStack-Provider-Data header with vllm_api_token All existing functionality is preserved while adding new dynamic capabilities. <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> ``` curl -X POST "http://localhost:8000/v1/chat/completions" -H "Authorization: Bearer my-dynamic-token" \ -H "X-LlamaStack-Provider-Data: {\"vllm_api_token\": \"Bearer my-dynamic-token\", \"vllm_url\": \"http://dynamic-server:8000\"}" \ -H "Content-Type: application/json" \ -d '{"model": "llama-3.1-8b", "messages": [{"role": "user", "content": "Hello!"}]}' ``` --------- Signed-off-by: Akram Ben Aissi <akram.benaissi@gmail.com>	2025-09-18 11:13:55 +02:00
Matthew Farrellee	49d4a5cc84	feat: add embedding and dynamic model support to Together inference adapter (#3458) ... # What does this PR do? adds embedding and dynamic model support to Together inference adapter - updated to use OpenAIMixin - workarounds for Together api quirks - recordings for together suite when subdirs=inference,pattern=openai ## Test Plan ``` $ TOGETHER_API_KEY=_NONE_ ./scripts/integration-tests.sh --stack-config server:ci-tests --setup together --subdirs inference --pattern openai ... tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:sanity] instantiating llama_stack_client Port 8321 is already in use, assuming server is already running... llama_stack_client instantiated in 0.121s PASSED [ 2%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:suffix] SKIPPED [ 4%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:completion:sanity] PASSED [ 6%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-1] SKIPPED [ 8%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free] SKIPPED [ 10%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_01] PASSED [ 12%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] PASSED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] SKIPPED [ 17%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 19%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 21%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free] SKIPPED [ 23%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 25%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 27%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 29%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 31%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 34%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 36%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 38%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 40%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 42%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-0] SKIPPED [ 46%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] SKIPPED [ 53%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 57%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 59%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 61%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 63%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 65%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 68%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 70%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 72%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] PASSED [ 74%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 76%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-emb=together/togethercomputer/m2-bert-80M-32k-retrieval] SKIPPED [ 78%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_01] PASSED [ 80%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] PASSED [ 82%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_01] SKIPPED [ 85%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 87%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-True] PASSED [ 89%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:non_streaming_02] PASSED [ 91%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] PASSED [ 93%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-inference:chat_completion:streaming_02] SKIPPED [ 95%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [ 97%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free-False] PASSED [100%] ============================================ 30 passed, 17 skipped, 50 deselected, 4 warnings in 21.96s ============================================= ```	2025-09-16 11:53:41 -07:00
Sébastien Han	65d45c7318	chore: various watsonx fixes (#3428) ... # What does this PR do? use a logger * update the distro to add the Files API otherwise it won't start since it is a dependency of vector * clarify project_id and api_key requirements * disable openai compatible calls since the endpoint returns 404 * disable text_inference structured format tests * fixed openai client initialization ## Test Plan Execute text_inference: ``` WATSONX_API_KEY=... WATSONX_PROJECT_ID=... python -m llama_stack.core.server.server llama_stack/distributions/watsonx/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -vvvv -ra --text-model watsonx/meta-llama/llama-3-3-70b-instruct tests/integration/inference/test_text_inference.py ============================================= test session starts ============================================== platform darwin -- Python 3.12.8, pytest-8.4.2, pluggy-1.6.0 -- /Users/leseb/Documents/AI/llama-stack/.venv/bin/python3 cachedir: .pytest_cache metadata: {'Python': '3.12.8', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.2', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0', 'hydra-core': '1.3.2'}} rootdir: /Users/leseb/Documents/AI/llama-stack configfile: pyproject.toml plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0, hydra-core-1.3.2 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 20 items tests/integration/inference/test_text_inference.py::test_text_completion_non_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:sanity] PASSED [ 5%] tests/integration/inference/test_text_inference.py::test_text_completion_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:sanity] PASSED [ 10%] tests/integration/inference/test_text_inference.py::test_text_completion_stop_sequence[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:stop_sequence] XFAIL [ 15%] tests/integration/inference/test_text_inference.py::test_text_completion_log_probs_non_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:log_probs] XFAIL [ 20%] tests/integration/inference/test_text_inference.py::test_text_completion_log_probs_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:log_probs] XFAIL [ 25%] tests/integration/inference/test_text_inference.py::test_text_completion_structured_output[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:structured_output] SKIPPED structured output) [ 30%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_non_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:non_streaming_01] PASSED [ 35%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:streaming_01] PASSED [ 40%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_tool_calling_and_non_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_calling] PASSED [ 45%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_tool_calling_and_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_calling] PASSED [ 50%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_tool_choice_required[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_calling] PASSED [ 55%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_tool_choice_none[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_calling] PASSED [ 60%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_structured_output[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:structured_output] SKIPPEDstructured output) [ 65%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_calling_tools_absent-True] PASSED [ 70%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_multi_turn_tool_calling[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:text_then_tool] XFAIL [ 75%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_non_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:non_streaming_02] PASSED [ 80%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:streaming_02] PASSED [ 85%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_calling_tools_absent-False] PASSED [ 90%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_multi_turn_tool_calling[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_then_answer] XFAIL [ 95%] tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_multi_turn_tool_calling[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:array_parameter] XFAIL [100%] =========================================== short test summary info ============================================ SKIPPED [2] tests/integration/inference/test_text_inference.py:49: Model watsonx/meta-llama/llama-3-3-70b-instruct hosted by remote::watsonx doesn't support json_schema structured output XFAIL tests/integration/inference/test_text_inference.py::test_text_completion_stop_sequence[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:stop_sequence] - remote::watsonx doesn't support 'stop' parameter yet XFAIL tests/integration/inference/test_text_inference.py::test_text_completion_log_probs_non_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:log_probs] - remote::watsonx doesn't support log probs yet XFAIL tests/integration/inference/test_text_inference.py::test_text_completion_log_probs_streaming[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:completion:log_probs] - remote::watsonx doesn't support log probs yet XFAIL tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_multi_turn_tool_calling[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:text_then_tool] - Not tested for non-llama4 models yet XFAIL tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_multi_turn_tool_calling[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:tool_then_answer] - Not tested for non-llama4 models yet XFAIL tests/integration/inference/test_text_inference.py::test_text_chat_completion_with_multi_turn_tool_calling[txt=watsonx/meta-llama/llama-3-3-70b-instruct-inference:chat_completion:array_parameter] - Not tested for non-llama4 models yet ============================ 12 passed, 2 skipped, 6 xfailed, 14 warnings in 36.88s ============================ ``` --------- Signed-off-by: Sébastien Han <seb@redhat.com>	2025-09-16 13:55:10 +02:00
Matthew Farrellee	f4ab154ade	feat: add dynamic model registration support to TGI inference (#3417) ... # What does this PR do? adds dynamic model support to TGI add new overwrite_completion_id feature to OpenAIMixin to deal with TGI always returning id="" ## Test Plan tgi: `docker run --gpus all --shm-size 1g -p 8080:80 -v /data:/data ghcr.io/huggingface/text-generation-inference --model-id Qwen/Qwen3-0.6B` stack: `TGI_URL=http://localhost:8080 uv run llama stack build --image-type venv --distro ci-tests --run` test: `./scripts/integration-tests.sh --stack-config http://localhost:8321 --setup tgi --subdirs inference --pattern openai`	2025-09-15 15:52:40 -04:00
Matthew Farrellee	8ef1189be7	chore: update the vLLM inference impl to use OpenAIMixin for openai-compat functions (#3404) ... # What does this PR do? update vLLM inference provider to use OpenAIMixin for openai-compat functions inference recordings from Qwen3-0.6B and vLLM 0.8.3 - ``` docker run --gpus all -v ~/.cache/huggingface:/root/.cache/huggingface -p 8000:8000 --ipc=host \ vllm/vllm-openai:latest \ --model Qwen/Qwen3-0.6B --enable-auto-tool-choice --tool-call-parser hermes ``` ## Test Plan ``` ./scripts/integration-tests.sh --stack-config server:ci-tests --setup vllm --subdirs inference ```	2025-09-11 09:04:38 -04:00
Sébastien Han	f31bcc11bc	feat: add Azure OpenAI inference provider support (#3396) ... # What does this PR do? Llama-stack now supports a new OpenAI compatible endpoint with Azure OpenAI. The starter distro has been updated to add the new remote inference provider. A few tests have been modified and improved. ## Test Plan Deploy a model in the Aure portal then: ``` $ AZURE_API_KEY=... AZURE_API_BASE=... uv run llama stack build --image-type venv --providers inference=remote::azure --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model azure/gpt-4.1 tests/integration/inference/test_openai_completion.py ... Results: ``` ============================================= test session starts ============================================== platform darwin -- Python 3.12.8, pytest-8.4.1, pluggy-1.6.0 -- /Users/leseb/Documents/AI/llama-stack/.venv/bin/python3 cachedir: .pytest_cache metadata: {'Python': '3.12.8', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.1', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0', 'hydra-core': '1.3.2'}} rootdir: /Users/leseb/Documents/AI/llama-stack configfile: pyproject.toml plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0, hydra-core-1.3.2 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 27 items tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=azure/gpt-5-mini-inference:completion:sanity] SKIPPED [ 3%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=azure/gpt-5-mini-inference:completion:suffix] SKIPPED [ 7%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=azure/gpt-5-mini-inference:completion:sanity] SKIPPED [ 11%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-1] SKIPPED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=azure/gpt-5-mini] SKIPPED [ 18%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01] PASSED [ 22%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 25%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 29%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-True] PASSED [ 33%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-True] PASSED [ 37%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=azure/gpt-5-mini] SKIPPEDed files.) [ 40%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=azure/gpt-5-mini-0] SKIPPED [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=azure/gpt-5-mini-False] PASSED [ 59%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=azure/gpt-5-mini-False] PASSED [ 62%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_01] PASSED [ 66%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 70%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_01] PASSED [ 74%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-True] PASSED [ 77%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-True] PASSED [ 81%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:non_streaming_02] PASSED [ 85%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 88%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=azure/gpt-5-mini-inference:chat_completion:streaming_02] PASSED [ 92%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=azure/gpt-5-mini-False] PASSED [ 96%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=azure/gpt-5-mini-False] PASSED [100%] =========================================== short test summary info ============================================ SKIPPED [3] tests/integration/inference/test_openai_completion.py:63: Model azure/gpt-5-mini hosted by remote::azure doesn't support OpenAI completions. SKIPPED [3] tests/integration/inference/test_openai_completion.py:118: Model azure/gpt-5-mini hosted by remote::azure doesn't support vllm extra_body parameters. SKIPPED [1] tests/integration/inference/test_openai_completion.py:124: Model azure/gpt-5-mini hosted by remote::azure doesn't support chat completion calls with base64 encoded files. ================================== 20 passed, 7 skipped, 2 warnings in 51.77s ================================== ``` Signed-off-by: Sébastien Han <seb@redhat.com>	2025-09-11 13:48:38 +02:00
Sumanth Kamenani	2838d5a20f	fix: AWS Bedrock inference profile ID conversion for region-specific endpoints (#3386) ... Fixes #3370 AWS switched to requiring region-prefixed inference profile IDs instead of foundation model IDs for on-demand throughput. This was causing ValidationException errors. Added auto-detection based on boto3 client region to convert model IDs like meta.llama3-1-70b-instruct-v1:0 to us.meta.llama3-1-70b-instruct-v1:0 depending on the detected region. Also handles edge cases like ARNs, case insensitive regions, and None regions. Tested with this request. ```json { "model_id": "meta.llama3-1-8b-instruct-v1:0", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "tell me a riddle" } ], "sampling_params": { "strategy": { "type": "top_p", "temperature": 0.7, "top_p": 0.9 }, "max_tokens": 512 } } ``` <img width="1488" height="878" alt="image" src="https://github.com/user-attachments/assets/0d61beec-3869-4a31-8f37-9f554c280b88" />	2025-09-11 11:41:53 +02:00
Sébastien Han	c86e45496e	ci: Re-enable pre-commit to fail (#3399) ... If pre-commit fails, the workflow must fail. --------- Signed-off-by: Sébastien Han <seb@redhat.com>	2025-09-10 10:00:46 -04:00
Matthew Farrellee	0e27016cf2	chore: update the vertexai inference impl to use openai-python for openai-compat functions (#3377) ... # What does this PR do? update VertexAI inference provider to use openai-python for openai-compat functions ## Test Plan ``` $ VERTEX_AI_PROJECT=... uv run llama stack build --image-type venv --providers inference=remote::vertexai --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model vertexai/vertex_ai/gemini-2.5-flash tests/integration/inference/test_openai_completion.py ... ``` i don't have an account to test this. `get_api_key` may also need to be updated per https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: Sébastien Han <seb@redhat.com>	2025-09-10 15:39:29 +02:00
Matthew Farrellee	6a35bd7bb6	chore: update the anthropic inference impl to use openai-python for openai-compat functions (#3366) ... # What does this PR do? update the Anthropic inference provider to use openai-python for the openai-compat endpoints ## Test Plan ci Co-authored-by: raghotham <rsm@meta.com>	2025-09-07 14:00:42 -07:00
Matthew Farrellee	d23607483f	chore: update the groq inference impl to use openai-python for openai-compat functions (#3348) ... # What does this PR do? update Groq inference provider to use OpenAIMixin for openai-compat endpoints changes on api.groq.com - - json_schema is now supported for specific models, see https://console.groq.com/docs/structured-outputs#supported-models - response_format with streaming is now supported for models that support response_format - groq no longer returns a 400 error if tools are provided and tool_choice is not "required" ## Test Plan ``` $ GROQ_API_KEY=... uv run llama stack build --image-type venv --providers inference=remote::groq --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model groq/llama-3.3-70b-versatile tests/integration/inference/test_openai_completion.py -k 'not store' ... SKIPPED [3] tests/integration/inference/test_openai_completion.py:44: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support OpenAI completions. SKIPPED [3] tests/integration/inference/test_openai_completion.py:94: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support vllm extra_body parameters. SKIPPED [4] tests/integration/inference/test_openai_completion.py:73: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support n param. SKIPPED [1] tests/integration/inference/test_openai_completion.py💯 Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support chat completion calls with base64 encoded files. ======================= 8 passed, 11 skipped, 8 deselected, 2 warnings in 5.13s ======================== ``` --------- Co-authored-by: raghotham <rsm@meta.com>	2025-09-06 15:36:27 -07:00
Matthew Farrellee	bf02cd846f	chore: update the sambanova inference impl to use openai-python for openai-compat functions (#3345) ... # What does this PR do? update SambaNova inference provider to use OpenAIMixin for openai-compat endpoints ## Test Plan ``` $ SAMBANOVA_API_KEY=... uv run llama stack build --image-type venv --providers inference=remote::sambanova --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model sambanova/Meta-Llama-3.3-70B-Instruct tests/integration/inference -k 'not store' ... FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=sambanova/Meta-Llama-3.3-70B-Instruct-inference:chat_completion:tool_calling_tools_absent-True] - AttributeError: 'NoneType' object has no attribute 'delta' FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=sambanova/Meta-Llama-3.3-70B-Instruct-inference:chat_completion:tool_calling_tools_absent-False] - llama_stack_client.InternalServerError: Error code: 500 - {'detail': 'Internal server error: An une... =========== 2 failed, 16 passed, 68 skipped, 8 deselected, 3 xfailed, 13 warnings in 15.85s ============ ``` the two failures also exist before this change. they are part of the deprecated inference.chat_completion tests that flow through litellm. they can be resolved later.	2025-09-06 12:25:13 -07:00
Matthew Farrellee	d6c3b36390	chore: update the gemini inference impl to use openai-python for openai-compat functions (#3351) ... # What does this PR do? update the Gemini inference provider to use openai-python for the openai-compat endpoints partially addresses #3349, does not address /inference/completion or /inference/chat-completion ## Test Plan ci	2025-09-06 12:22:20 -07:00
Ashwin Bharambe	c3d3a0b833	feat(tests): auto-merge all model list responses and unify recordings (#3320) ... One needed to specify record-replay related environment variables for running integration tests. We could not use defaults because integration tests could be run against Ollama instances which could be running different models. For example, text vs vision tests needed separate instances of Ollama because a single instance typically cannot serve both of these models if you assume the standard CI worker configuration on Github. As a result, `client.list()` as returned by the Ollama client would be different between these runs and we'd end up overwriting responses. This PR "solves" it by adding a small amount of complexity -- we store model list responses specially, keyed by the hashes of the models they return. At replay time, we merge all of them and pretend that we have the union of all models available. ## Test Plan Re-recorded all the tests using `scripts/integration-tests.sh --inference-mode record`, including the vision tests.	2025-09-03 11:33:03 -07:00
Cesare Pompeiano	ccaf6aaa51	chore(python-deps): replace ibm_watson_machine_learning with ibm_watsonx_ai (#3302) ... # What does this PR do? This PR updates the Watsonx provider dependencies from `ibm_watson_machine_learning` to `ibm_watsonx_ai`. The old package `ibm_watson_machine_learning` is in **deprecation mode** ([[PyPI link](https://pypi.org/project/ibm-watson-machine-learning/)](https://pypi.org/project/ibm-watson-machine-learning/)) and relies on older versions of dependencies such as `pandas`. Updating to `ibm_watsonx_ai` ensures compatibility with current dependency versions and ongoing support. ## Test Plan I verified the update by running an inference using a model provided by Watsonx. The model ran successfully, confirming that the new dependency works as expected. Co-authored-by: are-ces <cpompeia@redhat.com>	2025-09-03 11:33:35 +02:00
Jiayi Ni	b12cd528ef	docs: add VLM NIM example (#3277)	2025-08-29 16:23:52 -07:00
Matthew Farrellee	3d119a86d4	chore: indicate to mypy that InferenceProvider.batch_completion/batch_chat_completion is concrete (#3239) ... # What does this PR do? closes https://github.com/llamastack/llama-stack/issues/3236 mypy considered our default implementations (raise NotImplementedError) to be trivial. the result was we implemented the same stubs in providers. this change puts enough into the default impls so mypy considers them non-trivial. this allows us to remove the duplicate implementations.	2025-08-22 14:17:30 -07:00
Matthew Farrellee	2ee898cc4c	chore: indicate to mypy that InferenceProvider.rerank is concrete (#3238)	2025-08-22 12:02:13 -07:00
ehhuang	c5e2e269e2	feat(api): introduce /rerank (#2940) ... # What does this PR do? Context: https://github.com/meta-llama/llama-stack/issues/2937 The API design is inspired by existing offerings, but not exactly the same: * `top_n` as the parameter to control number of results, instead of `top_k`, since `n` is conventional to control number * `truncation` bool instead of `max_token_per_doc`, since we should just handle the truncation automatically depending on model capability, instead of user setting the context length manually. * `data` field in the response, to be consistent with other OpenAI APIs (though they don't have a rerank API). Also, it is one less name to learn in the API. ## Test Plan Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-08-21 18:23:16 -07:00
Mustafa Elbehery	c3b2b06974	refactor(logging): rename llama_stack logger categories (#3065) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> This PR renames categories of llama_stack loggers. This PR aligns logging categories as per the package name, as well as reviews from initial https://github.com/meta-llama/llama-stack/pull/2868. This is a follow up to #3061. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Replaces https://github.com/meta-llama/llama-stack/pull/2868 Part of https://github.com/meta-llama/llama-stack/issues/2865 cc @leseb @rhuss Signed-off-by: Mustafa Elbehery <melbeher@redhat.com>	2025-08-21 17:31:04 -07:00
Jiayi Ni	deffaa9e4e	fix: fix the error type in embedding test case (#3197) ... # What does this PR do? Currently the embedding integration test cases fail due to a misalignment in the error type. This PR fixes the embedding integration test by fixing the error type. ## Test Plan ``` pytest -s -v tests/integration/inference/test_embedding.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ```	2025-08-21 16:19:51 -07:00
Jiayi Ni	b72169ca47	docs: update the docs for NVIDIA Inference provider (#3227) ... # What does this PR do? - Documentation update and fix for the NVIDIA Inference provider. - Update the `run_moderation` for safety API with a `NotImplementedError` placeholder. Otherwise initialization NVIDIA inference client will raise an error. ## Test Plan N/A	2025-08-21 15:59:39 -07:00
Jiayi Ni	55e9959f62	fix: fix ``openai_embeddings`` for asymmetric embedding NIMs (#3205) ... # What does this PR do? NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. This PR adds the `input_type="query"` as default and updates the documentation to suggest using the `embedding` API for passage embeddings. <!-- If resolving an issue, uncomment and update the line below --> Resolves #2892 ## Test Plan ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ```	2025-08-20 08:06:25 -04:00
Mustafa Elbehery	3f8df167f3	chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) ... # What does this PR do? This PR adds a step in pre-commit to enforce using `llama_stack` logger. Currently, various parts of the code base uses different loggers. As a custom `llama_stack` logger exist and used in the codebase, it is better to standardize its utilization. Signed-off-by: Mustafa Elbehery <melbeher@redhat.com> Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>	2025-08-20 07:15:35 -04:00
Chacksu	fffdab4f5c	fix: Dell distribution missing kvstore (#3113) ... # What does this PR do? - Added kvstore config to ChromaDB provider config for Dell distribution similar to [starter config](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/distributions/starter/run.yaml#L110-L112) - Fixed [error](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/inference/_generated/_async_client.py#L3424-L3425) getting endpoint information by adding `hf-inference` as the provider to the `AsyncInferenceClient` (TGI client). ## Test Plan ``` export INFERENCE_PORT=8181 export DEH_URL=http://0.0.0.0:$INFERENCE_PORT export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct export CHROMADB_HOST=localhost export CHROMADB_PORT=8000 export CHROMA_URL=http://$CHROMADB_HOST:$CHROMADB_PORT export CUDA_VISIBLE_DEVICES=0 export LLAMA_STACK_PORT=8321 export HF_TOKEN=[redacted] # TGI Server docker run --rm -it \ --pull always \ --network host \ -v $HOME/.cache/huggingface:/data \ -e HF_TOKEN=$HF_TOKEN \ -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \ -p $INFERENCE_PORT:$INFERENCE_PORT \ --gpus all \ ghcr.io/huggingface/text-generation-inference:latest \ --dtype float16 \ --usage-stats off \ --sharded false \ --cuda-memory-fraction 0.8 \ --model-id meta-llama/Llama-3.2-3B-Instruct \ --port $INFERENCE_PORT \ --hostname 0.0.0.0 # Chrome DB docker run --rm -it \ --name chromadb \ --net=host -p 8000:8000 \ -v ~/chroma:/chroma/chroma \ -e IS_PERSISTENT=TRUE \ -e ANONYMIZED_TELEMETRY=FALSE \ chromadb/chroma:latest # Llama Stack llama stack run dell \ --port $LLAMA_STACK_PORT \ --env INFERENCE_MODEL=$INFERENCE_MODEL \ --env DEH_URL=$DEH_URL \ --env CHROMA_URL=$CHROMA_URL ``` --------- Co-authored-by: Connor Hack <connorhack@fb.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-08-13 06:18:25 -07:00
Ashwin Bharambe	3d90117891	chore(tests): fix responses and vector_io tests (#3119) ... Some fixes to MCP tests. And a bunch of fixes for Vector providers. I also enabled a bunch of Vector IO tests to be used with `LlamaStackLibraryClient` ## Test Plan Run Responses tests with llama stack library client: ``` pytest -s -v tests/integration/non_ci/responses/ --stack-config=server:starter \ --text-model openai/gpt-4o \ --embedding-model=sentence-transformers/all-MiniLM-L6-v2 \ -k "client_with_models" ``` Do the same with `-k openai_client` The rest should be taken care of by CI.	2025-08-12 16:15:53 -07:00
Nathan Weinberg	19123ca957	refactor: standardize InferenceRouter model handling (#2965)	2025-08-12 04:20:39 -06:00
Eran Cohen	a4bad6c0b4	feat: Add Google Vertex AI inference provider support (#2841) ... # What does this PR do? - Add new Vertex AI remote inference provider with litellm integration - Support for Gemini models through Google Cloud Vertex AI platform - Uses Google Cloud Application Default Credentials (ADC) for authentication - Added VertexAI models: gemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash. - Updated provider registry to include vertexai provider - Updated starter template to support Vertex AI configuration - Added comprehensive documentation and sample configuration <!-- If resolving an issue, uncomment and update the line below --> relates to https://github.com/meta-llama/llama-stack/issues/2747 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Eran Cohen <eranco@redhat.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>	2025-08-11 08:22:04 -04:00
Vlastimil Eliáš	1677d6bffd	feat: Flash-Lite 2.0 and 2.5 models added to Gemini inference provider (#3058) ... PR adds Flash-Lite 2.0 and 2.5 models to the Gemini inference provider Closes #3046 ## Test Plan I was not able to locate any existing test for this provider, so I performed manual testing. But the change is really trivial and straightforward.	2025-08-08 13:48:15 -07:00
Jiayi Ni	9e78f2da96	docs: fix the docs for NVIDIA Inference Provider (#3055) ... # What does this PR do? Fix the NVIDIA inference docs by updating API methods, model IDs, and embedding example. ## Test Plan N/A	2025-08-08 11:27:55 +02:00
Ashwin Bharambe	7f834339ba	chore(misc): make tests and starter faster (#3042) ... A bunch of miscellaneous cleanup focusing on tests, but ended up speeding up starter distro substantially. - Pulled llama stack client init for tests into `pytest_sessionstart` so it does not clobber output - Profiling of that told me where we were doing lots of heavy imports for starter, so lazied them - starter now starts 20seconds+ faster on my Mac - A few other smallish refactors for `compat_client`	2025-08-05 14:55:05 -07:00
Ashwin Bharambe	cc87995e2b	chore: rename templates to distributions (#3035) ... As the title says. Distributions is in, Templates is out. `llama stack build --template` --> `llama stack build --distro`. For backward compatibility, the previous option is kept but results in a warning. Updated `server.py` to remove the "config_or_template" backward compatibility since it has been a couple releases since that change.	2025-08-04 11:34:17 -07:00
IAN MILLER	a749d5f4a4	refactor: remove Conda support from Llama Stack (#2969) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> This PR is responsible for removal of Conda support in Llama Stack <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2539 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* -->	2025-08-02 15:52:59 -07:00
Matthew Farrellee	140ee7d337	fix: sambanova inference provider (#2996) ... # What does this PR do? closes #2995 update SambaNovaInferenceAdapter to efficiently use LiteLLMOpenAIMixin ## Test Plan ``` $ uv run pytest -s -v tests/integration/inference --stack-config inference=sambanova --text-model sambanova/Meta-Llama-3.1-8B-Instruct ... ======================== 10 passed, 84 skipped, 3 xfailed, 51 warnings in 8.14s ======================== ```	2025-08-01 09:09:14 -07:00
Ashwin Bharambe	2665f00102	chore(rename): move llama_stack.distribution to llama_stack.core (#2975) ... We would like to rename the term `template` to `distribution`. To prepare for that, this is a precursor. cc @leseb	2025-07-30 23:30:53 -07:00
Matthew Farrellee	60bb5e307e	feat(openai): add configurable base_url support with OPENAI_BASE_URL env var (#2919) ... # What does this PR do? - Add base_url field to OpenAIConfig with default "https://api.openai.com/v1" - Update sample_run_config to support OPENAI_BASE_URL environment variable - Modify get_base_url() to return configured base_url instead of hardcoded value - Add comprehensive test suite covering: - Default base URL behavior - Custom base URL from config - Environment variable override - Config precedence over environment variables - Client initialization with configured URL - Model availability checks using configured URL This enables users to configure custom OpenAI-compatible API endpoints via environment variables or configuration files. Closes #2910 ## Test Plan run unit tests	2025-07-28 10:16:02 -07:00
Matthew Farrellee	3c40c8e583	fix: litellm_provider_name for llama-api (#2934) ... litellm uses "meta_llama" for the provider name, see https://docs.litellm.ai/docs/providers/meta_llama ad https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py#L833	2025-07-28 10:02:16 -07:00
Ashwin Bharambe	9583f468f8	feat(starter)!: simplify starter distro; litellm model registry changes (#2916)	2025-07-25 15:02:04 -07:00
Ashwin Bharambe	1463b79218	feat(registry): make the Stack query providers for model listing (#2862) ... This flips #2823 and #2805 by making the Stack periodically query the providers for models rather than the providers going behind the back and calling "register" on to the registry themselves. This also adds support for model listing for all other providers via `ModelRegistryHelper`. Once this is done, we do not need to manually list or register models via `run.yaml` and it will remove both noise and annoyance (setting `INFERENCE_MODEL` environment variables, for example) from the new user experience. In addition, it adds a configuration variable `allowed_models` which can be used to optionally restrict the set of models exposed from a provider.	2025-07-24 10:39:53 -07:00
Matthew Farrellee	e33a50480d	fix: starter template and litellm backward compat conflict for openai (#2885) ... # What does this PR do? openai/models.py has backward compat entries for litellm model names. the starter template includes these in the list of registered models. the inclusion results in duplicate model registrations. the backward compat is no longer necessary. ## Test Plan ci	2025-07-24 17:28:37 +02:00
Matthew Farrellee	e1ed152779	chore: create OpenAIMixin for inference providers with an OpenAI-compat API that need to implement openai_* methods (#2835) ... # What does this PR do? add an `OpenAIMixin` for use by inference providers who remote endpoints support an OpenAI compatible API. use is demonstrated by refactoring - OpenAIInferenceAdapter - NVIDIAInferenceAdapter (adds embedding support) - LlamaCompatInferenceAdapter ## Test Plan existing unit and integration tests	2025-07-23 06:49:40 -04:00
ehhuang	8e1a2b4703	chore: remove *_openai_compat providers (#2849) ... # What does this PR do? These are no longer needed as llama-stack-evals can run against OAI endpoints directly. ## Test Plan	2025-07-22 10:25:36 -07:00
Ashwin Bharambe	199f859eec	feat(vllm): periodically refresh models (#2823) ... Just like #2805 but for vLLM. We also make VLLM_URL env variable optional (not required) -- if not specified, the provider silently sits idle and yells eventually if someone tries to call a completion on it. This is done so as to allow this provider to be present in the `starter` distribution. ## Test Plan Set up vLLM, copy the starter template and set `{ refresh_models: true, refresh_models_interval: 10 }` for the vllm provider and then run: ``` ENABLE_VLLM=vllm VLLM_URL=http://localhost:8000/v1 \ uv run llama stack run --image-type venv /tmp/starter.yaml ``` Verify that `llama-stack-client models list` brings up the model correctly from vLLM.	2025-07-18 15:53:09 -07:00
Ashwin Bharambe	68a2dfbad7	feat(ollama): periodically refresh models (#2805) ... For self-hosted providers like Ollama (or vLLM), the backing server is running a set of models. That server should be treated as the source of truth and the Stack registry should just be a cache for those models. Of course, in production environments, you may not want this (because you know what model you are running statically) hence there's a config boolean to control this behavior. _This is part of a series of PRs aimed at removing the requirement of needing to set `INFERENCE_MODEL` env variables for running Llama Stack server._ ## Test Plan Copy and modify the starter.yaml template / config and enable `refresh_models: true, refresh_models_interval: 10` for the ollama provider. Then, run: ``` LLAMA_STACK_LOGGING=all=debug \ ENABLE_OLLAMA=ollama uv run llama stack run --image-type venv /tmp/starter.yaml ``` See a gargantuan amount of logs, but verify that the provider is periodically refreshing models. Stop and prune a model from ollama server, restart the server. Verify that the model goes away when I call `uv run llama-stack-client models list`	2025-07-18 12:20:36 -07:00
Matthew Farrellee	477bcd4d09	feat: allow dynamic model registration for nvidia inference provider (#2726) ... # What does this PR do? let's users register models available at https://integrate.api.nvidia.com/v1/models that isn't already in llama_stack/providers/remote/inference/nvidia/models.py ## Test Plan 1. run the nvidia distro 2. register a model from https://integrate.api.nvidia.com/v1/models that isn't already know, as of this writing nvidia/llama-3.1-nemotron-ultra-253b-v1 is a good example 3. perform inference w/ the model	2025-07-17 12:11:30 -07:00
IAN MILLER	b57db11bed	feat: create dynamic model registration for OpenAI and Llama compat remote inference providers (#2745) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> The purpose of this task is to create a solution that can automatically detect when new models are added, deprecated, or removed by OpenAI and Llama API providers, and automatically update the list of supported models in LLamaStack. This feature is vitally important in order to avoid missing new models and editing the entries manually hence I created automation allowing users to dynamically register: - any models from OpenAI provider available at [https://api.openai.com/v1/models](https://api.openai.com/v1/models) that are not in [https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/openai/models.py](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/openai/models.py) - any models from Llama API provider available at [https://api.llama.com/v1/models](https://api.llama.com/v1/models) that are not in [https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/llama_openai_compat/models.py](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/llama_openai_compat/models.py) <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2504 this PR is dependant on #2710 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> 1. Create venv at root llamastack directory: `uv venv .venv --python 3.12 --seed` 2. Activate venv: `source .venv/bin/activate` 3. `uv pip install -e .` 4. Create OpenAI distro modifying run.yaml 5. Build distro: `llama stack build --template starter --image-type venv` 6. Then run LlamaStack, but before navigate to templates/starter folder: `llama stack run run.yaml --image-type venv OPENAI_API_KEY=<YOUR_KEY> ENABLE_OPENAI=openai` 7. Then try to register dummy llm that doesn't exist in OpenAI provider: ` llama-stack-client models register ianm/ianllm --provider-model-id=ianllm --provider-id=openai ` You should receive this output - combined list of static config + fetched available models from OpenAI: <img width="1380" height="474" alt="Screenshot 2025-07-14 at 12 48 50" src="https://github.com/user-attachments/assets/d26aad18-6b15-49ee-9c49-b01b2d33f883" /> 8. Then register real llm from OpenAI: llama-stack-client models register openai/gpt-4-turbo-preview --provider-model-id=gpt-4-turbo-preview --provider-id=openai <img width="1253" height="613" alt="Screenshot 2025-07-14 at 13 43 02" src="https://github.com/user-attachments/assets/60a5c9b1-3468-4eb9-9e92-cd7d21de3ca0" /> <img width="1288" height="655" alt="Screenshot 2025-07-14 at 13 43 11" src="https://github.com/user-attachments/assets/c1e48871-0e24-4bd9-a0b8-8c95552a51ee" /> We correctly fetched all available models from OpenAI As for Llama API, as a non-US person I don't have access to Llama API Key but I joined wait list. The implementation for Llama is the same as for OpenAI since Llama is openai compatible. So, the response from GET endpoint has the same structure as OpenAI https://llama.developer.meta.com/docs/api/models	2025-07-16 12:49:38 -04:00
Matthew Farrellee	a3e249807b	chore: remove vision model URL workarounds and simplify client creation (#2775) ... The vision models are now available at the standard URL, so the workaround code has been removed. This also simplifies the codebase by eliminating the need for per-model client caching. - Remove special URL handling for meta/llama-3.2-11b/90b-vision-instruct models - Convert _get_client method to _client property for cleaner API - Remove unnecessary lru_cache decorator and functools import - Simplify client creation logic to use single base URL for all models	2025-07-16 07:10:04 -07:00
Hardik Shah	6b8a8c1be9	fix: Safety in starter (#2731) ... - fireworks, together do not support Llama-guard 3 8b model anymore - Need to default to ollama - current safety shields logic was not correct since the shield_id was the provider ( which had duplicates ) - Followed similar logic to models Note: Seems a bit over-engineered but this can now be extended to other providers and fits in the overall mechanism of how env_vars are used to manage starter. ### How to test ``` ENABLE_OLLAMA=ollama ENABLE_FIREWORKS=fireworks SAFETY_MODEL=llama-guard3:1b pytest -s -v tests/integration/ --stack-config starter -k 'not(supervised_fine_tune or builtin_tool_code or safety_with_image or code_interpreter_for or rag_and_code or truncation or register_and_unregister)' --text-model fireworks/meta-llama/Llama-3.3-70B-Instruct --vision-model fireworks/meta-llama/Llama-4-Scout-17B-16E-Instruct --safety-shield llama-guard3:1b --embedding-model all-MiniLM-L6-v2 ``` ### Related but not obvious in this PR In the llama-stack-ops repo, we run tests before publishing packages and docker containers. The actions in that repo were using the fireworks / together distros ( which are non-existent ) So need to update that to run with `starter` and use `ollama` specifically for safety.	2025-07-14 15:07:40 -07:00
Ben Browning	51d9fd4808	fix: Don't cache clients for passthrough auth providers (#2728) ... # What does this PR do? Some of our inference providers support passthrough authentication via `x-llamastack-provider-data` header values. This fixes the providers that support passthrough auth to not cache their clients to the backend providers (mostly OpenAI client instances) so that the client connecting to Llama Stack has to provide those auth values on each and every request. ## Test Plan I added some unit tests to ensure we're not caching clients across requests for all the fixed providers in this PR. ``` uv run pytest -sv tests/unit/providers/inference/test_inference_client_caching.py ``` I also ran some of our OpenAI compatible API integration tests for each of the changed providers, just to ensure they still work. Note that these providers don't actually pass all these tests (for unrelated reasons due to quirks of the Groq and Together SaaS services), but enough of the tests passed to confirm the clients are still working as intended. ### Together ``` ENABLE_TOGETHER="together" \ uv run llama stack run llama_stack/templates/starter/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ uv run pytest -sv \ tests/integration/inference/test_openai_completion.py \ --text-model "together/meta-llama/Llama-3.1-8B-Instruct" ``` ### OpenAI ``` ENABLE_OPENAI="openai" \ uv run llama stack run llama_stack/templates/starter/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ uv run pytest -sv \ tests/integration/inference/test_openai_completion.py \ --text-model "openai/gpt-4o-mini" ``` ### Groq ``` ENABLE_GROQ="groq" \ uv run llama stack run llama_stack/templates/starter/run.yaml LLAMA_STACK_CONFIG=http://localhost:8321 \ uv run pytest -sv \ tests/integration/inference/test_openai_completion.py \ --text-model "groq/meta-llama/Llama-3.1-8B-Instruct" ``` --------- Signed-off-by: Ben Browning <bbrownin@redhat.com>	2025-07-11 13:38:27 -07:00
Jorge Piedrahita Ortiz	aa2595c7c3	fix: sambanova shields and model validation (#2693) ... # What does this PR do? Update the shield register validation of Sambanova not to raise, but only warn when a model is not available in the base url endpoint used, also added warnings when model is not available in the base url endpoint used <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> run starter distro with Sambanova enabled	2025-07-11 16:29:15 -04:00