# What does this PR do?
This PR adds two methods to the Inference API:
- `batch_completion`
- `batch_chat_completion`
The motivation is for evaluations targeting a local inference engine
(like meta-reference or vllm) where batch APIs provide for a substantial
amount of acceleration.
Why did I not add this to `Api.batch_inference` though? That just
resulted in a _lot_ more book-keeping given the structure of Llama
Stack. Had I done that, I would have needed to create a notion of a
"batch model" resource, setup routing based on that, etc. This does not
sound ideal.
So what's the future of the batch inference API? I am not sure. Maybe we
can keep it for true _asynchronous_ execution. So you can submit
requests, and it can return a Job instance, etc.
## Test Plan
Run meta-reference-gpu using:
```bash
export INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct
export INFERENCE_CHECKPOINT_DIR=../checkpoints/Llama-4-Scout-17B-16E-Instruct-20250331210000
export MODEL_PARALLEL_SIZE=4
export MAX_BATCH_SIZE=32
export MAX_SEQ_LEN=6144
LLAMA_MODELS_DEBUG=1 llama stack run meta-reference-gpu
```
Then run the batch inference test case.
# What does this PR do?
This stubs in some OpenAI server-side compatibility with three new
endpoints:
/v1/openai/v1/models
/v1/openai/v1/completions
/v1/openai/v1/chat/completions
This gives common inference apps using OpenAI clients the ability to
talk to Llama Stack using an endpoint like
http://localhost:8321/v1/openai/v1 .
The two "v1" instances in there isn't awesome, but the thinking is that
Llama Stack's API is v1 and then our OpenAI compatibility layer is
compatible with OpenAI V1. And, some OpenAI clients implicitly assume
the URL ends with "v1", so this gives maximum compatibility.
The openai models endpoint is implemented in the routing layer, and just
returns all the models Llama Stack knows about.
The following providers should be working with the new OpenAI
completions and chat/completions API:
* remote::anthropic (untested)
* remote::cerebras-openai-compat (untested)
* remote::fireworks (tested)
* remote::fireworks-openai-compat (untested)
* remote::gemini (untested)
* remote::groq-openai-compat (untested)
* remote::nvidia (tested)
* remote::ollama (tested)
* remote::openai (untested)
* remote::passthrough (untested)
* remote::sambanova-openai-compat (untested)
* remote::together (tested)
* remote::together-openai-compat (untested)
* remote::vllm (tested)
The goal to support this for every inference provider - proxying
directly to the provider's OpenAI endpoint for OpenAI-compatible
providers. For providers that don't have an OpenAI-compatible API, we'll
add a mixin to translate incoming OpenAI requests to Llama Stack
inference requests and translate the Llama Stack inference responses to
OpenAI responses.
This is related to #1817 but is a bit larger in scope than just chat
completions, as I have real use-cases that need the older completions
API as well.
## Test Plan
### vLLM
```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack build --template remote-vllm --image-type venv --run
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct"
```
### ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-q8_0"
```
## Documentation
Run a Llama Stack distribution that uses one of the providers mentioned
in the list above. Then, use your favorite OpenAI client to send
completion or chat completion requests with the base_url set to
http://localhost:8321/v1/openai/v1 . Replace "localhost:8321" with the
host and port of your Llama Stack server, if different.
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
## Test Plan
export MODEL=accounts/fireworks/models/llama4-scout-instruct-basic;
LLAMA_STACK_CONFIG=verification pytest -s -v tests/integration/inference
--vision-model $MODEL --text-model $MODEL
Running full Tool Calling required some updates to work e2e.
- Remove `python_start` and `python_end` tags
- Tool Call messages and Tool Resposne messages should end with
`<|eom|>`
- System prompt needed updates
```
You are a helpful assisant who can can answer general questions or invoke tools when necessary.
In addition to tool calls, you should also augment your responses by using the tool outputs.
```
### Test Plan
- Start server with meta-reference
```
LLAMA_STACK_DISABLE_VERSION_CHECK=1 LLAMA_MODELS_DEBUG=1 INFERENCE_MODEL=meta-llama/$MODEL llama stack run meta-reference-gpu
```
- Added **NEW** tests with 5 test cases for multi-turn tool calls
```
pytest -s -v --stack-config http://localhost:8321 tests/integration/inference/test_text_inference.py --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct
```
- Also verified all vision and agent tests pass
Previously, the integration tests started the server, but never really
used it because `--stack-config=ollama` uses the ollama template and the
inline "llama stack as library" client, not the HTTP client.
This PR makes sure we test it both ways.
We also add agents tests to the mix.
## Test Plan
GitHub
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
quick fix as the vision_inference test dog.jpg path has been changed.
[//]: # (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.*]
[//]: # (## Documentation)
# What does this PR do?
TTFT number largely depends on input length. Ideally we have a
"standard" test that we can use to measure against any llama stack
serving.
TODO: Once JSON is replaced with YAML, I will add "notes" for each test
to explain purpose of each test in place.
## Test plan
Please refer to e2e test doc for setup.
```
LLAMA_STACK_PORT=8322 pytest -v -s --stack-config="http://localhost:8322" \
--text-model="meta-llama/Llama-3.2-3B-Instruct" \
tests/integration/inference/test_text_inference.py::test_text_chat_completion_first_token_profiling
```
# What does this PR do?
Since we moved the move tests/client-sdk to tests/api in
https://github.com/meta-llama/llama-stack/pull/1376. The N999 rule is
not needed anymore. And furthermore in
abfbaf3c1b
[//]: # (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.*]
[//]: # (## Documentation)
Signed-off-by: Sébastien Han <seb@redhat.com>
You now run the integration tests with these options:
```bash
Custom options:
--stack-config=STACK_CONFIG
a 'pointer' to the stack. this can be either be:
(a) a template name like `fireworks`, or
(b) a path to a run.yaml file, or
(c) an adhoc config spec, e.g.
`inference=fireworks,safety=llama-guard,agents=meta-
reference`
--env=ENV Set environment variables, e.g. --env KEY=value
--text-model=TEXT_MODEL
comma-separated list of text models. Fixture name:
text_model_id
--vision-model=VISION_MODEL
comma-separated list of vision models. Fixture name:
vision_model_id
--embedding-model=EMBEDDING_MODEL
comma-separated list of embedding models. Fixture name:
embedding_model_id
--safety-shield=SAFETY_SHIELD
comma-separated list of safety shields. Fixture name:
shield_id
--judge-model=JUDGE_MODEL
comma-separated list of judge models. Fixture name:
judge_model_id
--embedding-dimension=EMBEDDING_DIMENSION
Output dimensionality of the embedding model to use for
testing. Default: 384
--record-responses Record new API responses instead of using cached ones.
--report=REPORT Path where the test report should be written, e.g.
--report=/path/to/report.md
```
Importantly, if you don't specify any of the models (text-model,
vision-model, etc.) the relevant tests will get **skipped!**
This will make running tests somewhat more annoying since all options
will need to be specified. We will make this easier by adding some easy
wrapper yaml configs.
## Test Plan
Example:
```bash
ashwin@ashwin-mbp ~/local/llama-stack/tests/integration (unify_tests) $
LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/test_text_inference.py \
--text-model meta-llama/Llama-3.2-3B-Instruct
```
Continues the refactor of tests.
Tests from `providers/tests` should be considered deprecated. For this
PR, I deleted most of the tests in
- inference
- safety
- agents
since much more comprehensive tests exist in
`tests/integration/{inference,safety,agents}` already.
I moved `test_persistence.py` from agents, but disabled all the tests
since that test needs to be properly migrated.
## Test Plan
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v agents --vision-inference-model=''
/Users/ashwin/homebrew/Caskroom/miniconda/base/envs/toolchain/lib/python3.10/site-packages/pytest_asyncio/plugin.py:208: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"
warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
======================================================================================================= test session starts ========================================================================================================
platform darwin -- Python 3.10.16, pytest-8.3.3, pluggy-1.5.0 -- /Users/ashwin/homebrew/Caskroom/miniconda/base/envs/toolchain/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.10.16', 'Platform': 'macOS-15.3.1-arm64-arm-64bit', 'Packages': {'pytest': '8.3.3', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.24.0', 'html': '4.1.1', 'metadata': '3.1.1', 'anyio': '4.8.0', 'nbval': '0.11.0'}}
rootdir: /Users/ashwin/local/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.24.0, html-4.1.1, metadata-3.1.1, anyio-4.8.0, nbval-0.11.0
asyncio: mode=strict, default_loop_scope=None
collected 15 items
agents/test_agents.py::test_agent_simple[txt=8B] PASSED
agents/test_agents.py::test_tool_config[txt=8B] PASSED
agents/test_agents.py::test_builtin_tool_web_search[txt=8B] PASSED
agents/test_agents.py::test_builtin_tool_code_execution[txt=8B] PASSED
agents/test_agents.py::test_code_interpreter_for_attachments[txt=8B] PASSED
agents/test_agents.py::test_custom_tool[txt=8B] PASSED
agents/test_agents.py::test_custom_tool_infinite_loop[txt=8B] PASSED
agents/test_agents.py::test_tool_choice[txt=8B] PASSED
agents/test_agents.py::test_rag_agent[txt=8B-builtin::rag/knowledge_search] PASSED
agents/test_agents.py::test_rag_agent[txt=8B-builtin::rag] PASSED
agents/test_agents.py::test_rag_agent_with_attachments[txt=8B] PASSED
agents/test_agents.py::test_rag_and_code_agent[txt=8B] PASSED
agents/test_agents.py::test_create_turn_response[txt=8B] PASSED
agents/test_persistence.py::test_delete_agents_and_sessions SKIPPED (This test needs to be migrated to api / client-sdk world)
agents/test_persistence.py::test_get_agent_turns_and_steps SKIPPED (This test needs to be migrated to api / client-sdk world)
```
