9 commits

Author	SHA1	Message	Date
Ashwin Bharambe	08b4a1deb3	feat(tests): introduce inference record/replay to increase test reliability (#2941) ... Implements a comprehensive recording and replay system for inference API calls that eliminates dependency on online inference providers during testing. The system treats inference as deterministic by recording real API responses and replaying them in subsequent test runs. Applies to OpenAI clients (which should cover many inference requests) as well as Ollama AsyncClient. For storing, we use a hybrid system: Sqlite for fast lookups and JSON files for easy greppability / debuggability. As expected, tests become much much faster (more than 3x in just inference testing.) ```bash LLAMA_STACK_TEST_INFERENCE_MODE=record LLAMA_STACK_TEST_RECORDING_DIR=<...> \ uv run pytest -s -v tests/integration/inference \ --stack-config=starter \ -k "not( builtin_tool or safety_with_image or code_interpreter or test_rag )" \ --text-model="ollama/llama3.2:3b-instruct-fp16" \ --embedding-model=sentence-transformers/all-MiniLM-L6-v2 ``` ```bash LLAMA_STACK_TEST_INFERENCE_MODE=replay LLAMA_STACK_TEST_RECORDING_DIR=<...> \ uv run pytest -s -v tests/integration/inference \ --stack-config=starter \ -k "not( builtin_tool or safety_with_image or code_interpreter or test_rag )" \ --text-model="ollama/llama3.2:3b-instruct-fp16" \ --embedding-model=sentence-transformers/all-MiniLM-L6-v2 ``` - `LLAMA_STACK_TEST_INFERENCE_MODE`: `live` (default), `record`, or `replay` - `LLAMA_STACK_TEST_RECORDING_DIR`: Storage location (must be specified for record or replay modes)	2025-07-29 12:41:31 -07:00
Ashwin Bharambe	3b83032555	feat(registry): more flexible model lookup (#2859) ... This PR updates model registration and lookup behavior to be slightly more general / flexible. See https://github.com/meta-llama/llama-stack/issues/2843 for more details. Note that this change is backwards compatible given the design of the `lookup_model()` method. ## Test Plan Added unit tests	2025-07-22 15:22:48 -07:00
Sébastien Han	ac5fd57387	chore: remove nested imports (#2515) ... # What does this PR do? * Given that our API packages use "import *" in `__init.py__` we don't need to do `from llama_stack.apis.models.models` but simply from llama_stack.apis.models. The decision to use `import *` is debatable and should probably be revisited at one point. * Remove unneeded Ruff F401 rule * Consolidate Ruff F403 rule in the pyprojectfrom llama_stack.apis.models.models Signed-off-by: Sébastien Han <seb@redhat.com>	2025-06-26 08:01:05 +05:30
Charlie Doern	d12f195f56	feat: drop python 3.10 support (#2469) ... # What does this PR do? dropped python3.10, updated pyproject and dependencies, and also removed some blocks of code with special handling for enum.StrEnum Closes #2458 Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-06-19 12:07:14 +05:30
Hardik Shah	985d0b156c	feat: Add suffix to openai_completions (#2449) ... For code completion apps need "fill in the middle" capabilities. Added option of `suffix` to `openai_completion` to enable this. Updated ollama provider to showcase the same. ### Test Plan ``` pytest -sv --stack-config="inference=ollama" tests/integration/inference/test_openai_completion.py --text-model qwen2.5-coder:1.5b -k test_openai_completion_non_streaming_suffix ``` ### OpenAI Sample script ``` from openai import OpenAI client = OpenAI(base_url="http://localhost:8321/v1/openai/v1") response = client.completions.create( model="qwen2.5-coder:1.5b", prompt="The capital of ", suffix="is Paris.", max_tokens=10, ) print(response.choices[0].text) ``` ### Output ``` France is ____. To answer this question, we ```	2025-06-13 16:06:06 -07:00
Rohan Awhad	4e37b49cdc	fix: #1867 InferenceRouter has no attribute formatter (#2422) ... # What does this PR do? Closes #1867 [Steps to reproduce the bug](https://github.com/meta-llama/llama-stack/issues/1867#issuecomment-2956819381) The change was designed to minimize code changes. Open to option of skipping `metrics` field entirely when `telemetry` is disabled. ## Test Plan 1. Build llama-stack remote-vllm container ```bash llama stack build --template remote-vllm --image-type container ``` 2. Create a small run.yaml ```yaml version: '2' image_name: remote-vllm apis: - inference providers: inference: - provider_id: vllm-inference provider_type: remote::vllm config: url: ${env.VLLM_URL:http://localhost:8000/v1} max_tokens: ${env.VLLM_MAX_TOKENS:4096} api_token: ${env.VLLM_API_TOKEN:fake} tls_verify: ${env.VLLM_TLS_VERIFY:true} metadata_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db inference_store: type: sqlite db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/inference_store.db models: - metadata: {} model_id: ${env.INFERENCE_MODEL} provider_id: vllm-inference model_type: llm shields: [] vector_dbs: [] datasets: [] scoring_fns: [] benchmarks: [] server: port: 8321 ``` 3. Run the llama-stack server ```bash export VLLM_URL="http://localhost:8000/v1" export INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack run run.yaml ``` 4. Then perform a curl ```bash curl -X 'POST' \ 'http://localhost:8321/v1/inference/completion' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "model_id": "meta-llama/Llama-3.2-3B-Instruct", "content": "string", "sampling_params": { "strategy": { "type": "greedy" }, "max_tokens": 10, "repetition_penalty": 1, "stop": [ "string" ] }, "stream": false, "logprobs": { "top_k": 0 } }' ``` 5. You should receive a 200 response with metric values set to 0, similar to one below: ``` { "metrics": [ { "metric": "prompt_tokens", "value": 0, "unit": null }, { "metric": "completion_tokens", "value": 0, "unit": null }, { "metric": "total_tokens", "value": 0, "unit": null } ], [...] } ``` Co-authored-by: Rohan Awhad <rawhad@redhat.com>	2025-06-11 18:14:41 +02:00
Sumit Jaiswal	33ecefd284	feat: To add health status check for remote VLLM (#2303) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> To add health status check for remote VLLM <!-- 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.* --> PR includes the unit test to test the added health check implementation feature.	2025-06-06 15:33:12 -04:00
Hardik Shah	b21050935e	feat: New OpenAI compat embeddings API (#2314) ... # What does this PR do? Adds a new endpoint that is compatible with OpenAI for embeddings api. `/openai/v1/embeddings` Added providers for OpenAI, LiteLLM and SentenceTransformer. ## Test Plan ``` LLAMA_STACK_CONFIG=http://localhost:8321 pytest -sv tests/integration/inference/test_openai_embeddings.py --embedding-model all-MiniLM-L6-v2,text-embedding-3-small,gemini/text-embedding-004 ```	2025-05-31 22:11:47 -07:00
Ashwin Bharambe	eedf21f19c	chore: split routers into individual files (inference, tool, vector_io, eval_scoring) (#2258)	2025-05-24 22:59:07 -07:00

Renamed from llama_stack/distribution/routers/routers.py (Browse further)