# What does this PR do?
NVIDIA Inference provider was using the ModelRegistryHelper to map input
model ids to provider model ids. this updates it to use the model_store.
## Test Plan
`LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest -v
tests/integration/inference/{test_embedding.py,test_text_inference.py,test_openai_completion.py}
--embedding-model nvidia/llama-3.2-nv-embedqa-1b-v2
--text-model=meta-llama/Llama-3.1-70B-Instruct`
Test plan:
python tests/verifications/generate_report.py --providers
fireworks,together,llama_meta_ref,openai
Co-authored-by: Eric Huang <erichuang@fb.com>
# What does this PR do?
Allow users to name an agent and use the name in telemetry instead of
relying on randomly generated agent_ids. This improves the developer
experience by making it easier to find specific agents in telemetry
logs.
Closes#1832
## Test Plan
- Added tests to verify the agent name is properly stored and retrieved
- Ran `uv run -- pytest -v
tests/integration/telemetry/test_telemetry.py::test_agent_name_filtering`
from the root of the project and made sure the tests pass
- Ran `uv run -- pytest -v
tests/integration/telemetry/test_telemetry.py::test_agent_query_spans`
to verify existing code without agent names still works correctly
## Use Example
```
agent = Agent(
llama_stack_client,
model=text_model_id,
name="CustomerSupportAgent", # New parameter
instructions="You are a helpful customer support assistant"
)
session_id = agent.create_session(f"test-session-{uuid4()}")
```
## Implementation Notes
- Agent names are optional string parameters with no additional
validation
- Names are not required to be unique - multiple agents can have the
same name
- The agent_id remains the unique identifier for an agent
---------
Co-authored-by: raghotham <raghotham@gmail.com>
# What does this PR do?
Add NVIDIA platform docs that serve as a starting point for Llama Stack
users and explains all supported microservices.
[//]: # (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)
---------
Co-authored-by: Jash Gulabrai <jgulabrai@nvidia.com>
# What does this PR do?
This PR handles the case where a Customization Job's status is
`unknown`. Since we don't map `unknown` to a valid `JobStatus`, the
PostTraining provider throws an exception when fetching/listing a job.
[//]: # (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.*]
`./scripts/unit-tests.sh
tests/unit/providers/nvidia/test_supervised_fine_tuning.py` succeeds
[//]: # (## Documentation)
Co-authored-by: Jash Gulabrai <jgulabrai@nvidia.com>
# What does this PR do?
Adds `meta/llama-3.2-1b-instruct` to list of models that NeMo Customizer
can fine-tune. This is the model our example notebooks typically use for
fine-tuning.
[//]: # (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)
Co-authored-by: Jash Gulabrai <jgulabrai@nvidia.com>
Fixes: #1955
Since 0.2.0, the vLLM gets an empty list (vs ``None``in 0.1.9 and
before) when there are no tools configured which causes the issue
described in #1955 p. This patch avoids sending the 'tools' param to the
vLLM altogether instead of an empty list.
It also adds a small unit test to avoid regressions.
The OpenAI
[specification](https://platform.openai.com/docs/api-reference/chat/create)
does not explicitly state that the list cannot be empty but I found this
out through experimentation and it might depend on the actual remote
vllm. In any case, as this parameter is Optional, is best to skip it
altogether if there's no tools configured.
Signed-off-by: Daniel Alvarez <dalvarez@redhat.com>
# What does this PR do?
ollama's CLI supports running models via commands such as 'ollama run
llama3.2' this syntax does not work with the INFERENCE_MODEL llamastack
var as currently specifying a tag such as 'latest' is required
this commit will check to see if the 'latest' model is available and use
that model if a user passes a model name without a tag but the 'latest'
is available in ollama
## Test Plan
Behavior pre-code change
```bash
$ INFERENCE_MODEL=llama3.2 llama stack build --template ollama --image-type venv --run
...
INFO 2025-04-08 13:42:42,842 llama_stack.providers.remote.inference.ollama.ollama:80 inference: checking
connectivity to Ollama at `http://beanlab1.bss.redhat.com:11434`...
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/server/server.py", line 502, in <module>
main()
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/server/server.py", line 401, in main
impls = asyncio.run(construct_stack(config))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.12/asyncio/runners.py", line 195, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.12/asyncio/base_events.py", line 691, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/stack.py", line 222, in construct_stack
await register_resources(run_config, impls)
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/stack.py", line 99, in register_resources
await method(**obj.model_dump())
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/providers/utils/telemetry/trace_protocol.py", line 102, in async_wrapper
result = await method(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/routers/routing_tables.py", line 294, in register_model
registered_model = await self.register_object(model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/routers/routing_tables.py", line 228, in register_object
registered_obj = await register_object_with_provider(obj, p)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/distribution/routers/routing_tables.py", line 77, in register_object_with_provider
return await p.register_model(obj)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/providers/utils/telemetry/trace_protocol.py", line 102, in async_wrapper
result = await method(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/nathan/ai/llama-stack/repos/llama-stack/llama_stack/providers/remote/inference/ollama/ollama.py", line 315, in register_model
raise ValueError(
ValueError: Model 'llama3.2' is not available in Ollama. Available models: llama3.2:latest
++ error_handler 108
++ echo 'Error occurred in script at line: 108'
Error occurred in script at line: 108
++ exit 1
```
Behavior post-code change
```bash
$ INFERENCE_MODEL=llama3.2 llama stack build --template ollama --image-type venv --run
...
INFO 2025-04-08 13:58:17,365 llama_stack.providers.remote.inference.ollama.ollama:80 inference: checking
connectivity to Ollama at `http://beanlab1.bss.redhat.com:11434`...
WARNING 2025-04-08 13:58:18,190 llama_stack.providers.remote.inference.ollama.ollama:317 inference: Imprecise provider
resource id was used but 'latest' is available in Ollama - using 'llama3.2:latest'
INFO 2025-04-08 13:58:18,191 llama_stack.providers.remote.inference.ollama.ollama:308 inference: Pulling embedding
model `all-minilm:latest` if necessary...
INFO 2025-04-08 13:58:18,799 __main__:478 server: Listening on ['::', '0.0.0.0']:8321
INFO: Started server process [28378]
INFO: Waiting for application startup.
INFO 2025-04-08 13:58:18,803 __main__:148 server: Starting up
INFO: Application startup complete.
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
...
```
## Documentation
Did not document this anywhere but happy to do so if there is an
appropriate place
Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
# What does this PR do?
Now a separate thread is started to execute training jobs. Training
requests now return job ID before the job completes. (Which fixes API
timeouts for any jobs that take longer than a minute.)
Note: the scheduler code is meant to be spun out in the future into a
common provider service that can be reused for different APIs and
providers. It is also expected to back the /jobs API proposed here:
https://github.com/meta-llama/llama-stack/discussions/1238
Hence its somewhat generalized form which is expected to simplify its
adoption elsewhere in the future.
Note: this patch doesn't attempt to implement missing APIs (e.g. cancel
or job removal). This work will belong to follow-up PRs.
[//]: # (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.*]
Added unit tests for the scheduler module. For the API coverage, did
manual testing and was able to run a training cycle on GPU. The initial
call returned job ID before the training completed, as (now) expected.
Artifacts are returned as expected.
```
JobArtifactsResponse(checkpoints=[{'identifier': 'meta-llama/Llama-3.2-3B-Instruct-sft-0', 'created_at': '2025-03-07T22:45:19.892714', 'epoch': 0, 'post_training_job_id': 'test-job2ee77104-2fd3-4a4e-84cf-f83f8b8f1f50', 'path': '/home/ec2-user/.llama/checkpoints/meta-llama/Llama-3.2-3B-Instruct-sft-0', 'training_metrics': None}], job_uuid='test-job2ee77104-2fd3-4a4e-84cf-f83f8b8f1f50')
```
The integration test is currently disabled for the provider. I will look
into how it can be enabled in a different PR / issue context.
[//]: # (## Documentation)
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
TLDR: Changes needed to get 100% passing tests for OpenAI API
verification tests when run against Llama Stack with the `together`,
`fireworks`, and `openai` providers. And `groq` is better than before,
at 88% passing.
This cleans up the OpenAI API support for image message types
(specifically `image_url` types) and handling of the `response_format`
chat completion parameter. Both of these required a few more Pydantic
model definitions in our Inference API, just to move from the
not-quite-right stubs I had in place to something fleshed out to match
the actual OpenAI API specs.
As part of testing this, I also found and fixed a bug in the litellm
implementation of openai_completion and openai_chat_completion, so the
providers based on those should actually be working now.
The method `prepare_openai_completion_params` in
`llama_stack/providers/utils/inference/openai_compat.py` was improved to
actually recursively clean up input parameters, including handling of
lists, dicts, and dumping of Pydantic models to dicts. These changes
were required to get to 100% passing tests on the OpenAI API
verification against the `openai` provider.
With the above, the together.ai provider was passing as well as it is
without Llama Stack. But, since we have Llama Stack in the middle, I
took the opportunity to clean up the together.ai provider so that it now
also passes the OpenAI API spec tests we have at 100%. That means
together.ai is now passing our verification test better when using an
OpenAI client talking to Llama Stack than it is when hitting together.ai
directly, without Llama Stack in the middle.
And, another round of work for Fireworks to improve translation of
incoming OpenAI chat completion requests to Llama Stack chat completion
requests gets the fireworks provider passing at 100%. The server-side
fireworks.ai tool calling support with OpenAI chat completions and Llama
4 models isn't great yet, but by pointing the OpenAI clients at Llama
Stack's API we can clean things up and get everything working as
expected for Llama 4 models.
## Test Plan
### OpenAI API Verification Tests
I ran the OpenAI API verification tests as below and 100% of the tests
passed.
First, start a Llama Stack server that runs the `openai` provider with
the `gpt-4o` and `gpt-4o-mini` models deployed. There's not a template
setup to do this out of the box, so I added a
`tests/verifications/openai-api-verification-run.yaml` to do this.
First, ensure you have the necessary API key environment variables set:
```
export TOGETHER_API_KEY="..."
export FIREWORKS_API_KEY="..."
export OPENAI_API_KEY="..."
```
Then, run a Llama Stack server that serves up all these providers:
```
llama stack run \
--image-type venv \
tests/verifications/openai-api-verification-run.yaml
```
Finally, generate a new verification report against all these providers,
both with and without the Llama Stack server in the middle.
```
python tests/verifications/generate_report.py \
--run-tests \
--provider \
together \
fireworks \
groq \
openai \
together-llama-stack \
fireworks-llama-stack \
groq-llama-stack \
openai-llama-stack
```
You'll see that most of the configurations with Llama Stack in the
middle now pass at 100%, even though some of them do not pass at 100%
when hitting the backend provider's API directly with an OpenAI client.
### OpenAI Completion Integration Tests with vLLM:
I also ran the smaller `test_openai_completion.py` test suite (that's
not yet merged with the verification tests) on multiple of the
providers, since I had to adjust the method signature of
openai_chat_completion a bit and thus had to touch lots of these
providers to match. Here's the tests I ran there, all passing:
```
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
```
in another terminal
```
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"
```
### OpenAI Completion Integration Tests with ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run
```
in another terminal
```
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"
```
### OpenAI Completion Integration Tests with together.ai
```
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct-Turbo" llama stack build --template together --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct-Turbo" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct-Turbo"
```
### OpenAI Completion Integration Tests with fireworks.ai
```
INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" llama stack build --template fireworks --image-type venv --run
```
in another terminal
```
LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.1-8B-Instruct"
---------
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# 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?
Today, supervised_fine_tune itself and the `TrainingConfig` class have a
bunch of required fields that a provider implementation might not need.
for example, if a provider wants to handle hyperparameters in its
configuration as well as any type of dataset retrieval, optimizer or
LoRA config, a user will still need to pass in a virtually empty
`DataConfig`, `OptimizerConfig` and `AlgorithmConfig` in some cases.
Many of these fields are intended to work specifically with llama models
and knobs intended for customizing inline.
Adding remote post_training providers will require loosening these
arguments, or forcing users to pass in empty objects to satisfy the
pydantic models.
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# 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?
This PR adds unit tests for the NVIDIA Safety provider implementation.
[//]: # (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.*]
1. Ran `./scripts/unit-tests.sh
tests/unit/providers/nvidia/test_safety.py` from the root of the
project. Verified tests pass.
```
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_init_nemo_guardrails Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_init_nemo_guardrails_invalid_temperature Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_register_shield_with_valid_id Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_register_shield_without_id Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_run_shield_allowed Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_run_shield_blocked Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_run_shield_http_error Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
tests/unit/providers/nvidia/test_safety.py::TestNVIDIASafetyAdapter::test_run_shield_not_found Initializing NVIDIASafetyAdapter(http://nemo.test)...
PASSED
```
[//]: # (## Documentation)
---------
Co-authored-by: Jash Gulabrai <jgulabrai@nvidia.com>
# What does this PR do?
The supervised_fine_tune method in NvidiaPostTrainingAdapter had some
extra args that aren't part of the post_training protocol, and these
extra args were causing FastAPI to throw an error when attempting to
stand up an endpoint that used this provider.
(Closes#1938)
## Test Plan
Before this change, bringing up a stack with the `nvidia` template
failed. Afterwards, it passes. I'm testing this like:
```
INFERENCE_MODEL="meta/llama-3.1-8b-instruct" \
llama stack build --template nvidia --image-type venv --run
```
I also ensured the nvidia/test_supervised_fine_tuning.py tests still
pass via:
```
python -m pytest \
tests/unit/providers/nvidia/test_supervised_fine_tuning.py
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
# What does this PR do?
While building the "experimental-post-training" distribution, we
encountered a version conflict between torchao with inference requiring
version 0.5.0 and training currently depending on version 0.8.0.
Resolves this error:
```
× No solution found when resolving dependencies:
╰─▶ Because you require torchao==0.5.0 and torchao==0.8.0, we can conclude that your requirements are unsatisfiable.
ERROR 2025-04-10 10:41:22,597 llama_stack.distribution.build:128 uncategorized: Failed to build target test with
return code 1
```
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
closes#1853
## Test Plan
```
uv run llama stack build --image-type conda --image-name ollama --config llama_stack/templates/ollama/build.yaml
ollama pull llama3.2:3b
LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/integration/inference/test_text_inference.py -v --text-model=llama3.2:3b
```
# 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 $MODEL
# What does this PR do?
Move around bits. This makes the copies from llama-models _much_ easier
to maintain and ensures we don't entangle meta-reference specific
tidbits into llama-models code even by accident.
Also, kills the meta-reference-quantized-gpu distro and rolls
quantization deps into meta-reference-gpu.
## Test Plan
```
LLAMA_MODELS_DEBUG=1 \
with-proxy llama stack run meta-reference-gpu \
--env INFERENCE_MODEL=meta-llama/Llama-4-Scout-17B-16E-Instruct \
--env INFERENCE_CHECKPOINT_DIR=<DIR> \
--env MODEL_PARALLEL_SIZE=4 \
--env QUANTIZATION_TYPE=fp8_mixed
```
Start a server with and without quantization. Point integration tests to
it using:
```
pytest -s -v tests/integration/inference/test_text_inference.py \
--stack-config http://localhost:8321 --text-model meta-llama/Llama-4-Scout-17B-16E-Instruct
```
Running full Tool Calling required some updates to work e2e.
- Remove `python_start` and `python_end` tags
- Tool Call messages and Tool Resposne messages should end with
`<|eom|>`
- System prompt needed updates
```
You are a helpful assisant who can can answer general questions or invoke tools when necessary.
In addition to tool calls, you should also augment your responses by using the tool outputs.
```
### Test Plan
- Start server with meta-reference
```
LLAMA_STACK_DISABLE_VERSION_CHECK=1 LLAMA_MODELS_DEBUG=1 INFERENCE_MODEL=meta-llama/$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
# What does this PR do?
- **chore: mypy for strong_typing**
- **chore: mypy for remote::vllm**
- **chore: mypy for remote::ollama**
- **chore: mypy for providers.datatype**
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Don't return list for runtime tools. Instead return Response object for
pagination and consistency with other APIs.
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Move pagination logic from LocalFS and HuggingFace implementations into
a common helper function to ensure consistent pagination behavior across
providers. This reduces code duplication and centralizes pagination
logic in one place.
## Test Plan
Run this script:
```
from llama_stack_client import LlamaStackClient
# Initialize the client
client = LlamaStackClient(base_url="http://localhost:8321")
# Register a dataset
response = client.datasets.register(
purpose="eval/messages-answer", # or "eval/question-answer" or "post-training/messages"
source={"type": "uri", "uri": "huggingface://datasets/llamastack/simpleqa?split=train"},
dataset_id="my_dataset", # optional, will be auto-generated if not provided
metadata={"description": "My evaluation dataset"}, # optional
)
# Verify the dataset was registered by listing all datasets
datasets = client.datasets.list()
print(f"Registered datasets: {[d.identifier for d in datasets]}")
# You can then access the data using the datasetio API
# rows = client.datasets.iterrows(dataset_id="my_dataset", start_index=1, limit=2)
rows = client.datasets.iterrows(dataset_id="my_dataset")
print(f"Data: {rows.data}")
```
And play with `start_index` and `limit`.
[//]: # (## Documentation)
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
https://github.com/meta-llama/llama-stack/pull/1828 removed
__root_span__ attribute which is still needed
## Test Plan
added telemetry integration test
LLAMA_STACK_CONFIG=http://localhost:5001 pytest -s -v
tests/integration/telemetry --safety-shield meta-llama/Llama-Guard-3-8B
--text-model accounts/fireworks/models/llama-v3p3-70b-instruct
# What does this PR do?
This PR converts blocking Milvus Client calls to non-blocking.
Another one for https://github.com/meta-llama/llama-stack/issues/1489
## Test Plan
I ran the integration tests from
https://github.com/meta-llama/llama-stack/pull/1467 with:
```python
pytest -s -v tests/integration/vector_io/test_vector_io.py \
--stack-config inference=sentence-transformers,vector_io=inline::milvus \
--embedding-model all-miniLM-L6-V2 --env MILVUS_DB_PATH=/tmp/moo.db
INFO 2025-03-28 21:35:22,726 tests.integration.conftest:41 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS
/Users/farceo/dev/llama-stack/.venv/lib/python3.10/site-packages/pytest_asyncio/plugin.py:207: 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-8.3.4, pluggy-1.5.0 -- /Users/farceo/dev/llama-stack/.venv/bin/python3
cachedir: .pytest_cache
metadata: {'Python': '3.10.16', 'Platform': 'macOS-15.3.1-arm64-arm-64bit', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'cov': '6.0.0', 'html': '4.1.1', 'metadata': '3.1.1', 'asyncio': '0.25.3', 'anyio': '4.8.0', 'nbval': '0.11.0'}}
rootdir: /Users/farceo/dev/llama-stack
configfile: pyproject.toml
plugins: cov-6.0.0, html-4.1.1, metadata-3.1.1, asyncio-0.25.3, anyio-4.8.0, nbval-0.11.0
asyncio: mode=strict, asyncio_default_fixture_loop_scope=None
collected 7 items
tests/integration/vector_io/test_vector_io.py::test_vector_db_retrieve[emb=all-miniLM-L6-V2] PASSED
tests/integration/vector_io/test_vector_io.py::test_vector_db_register[emb=all-miniLM-L6-V2] PASSED
tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=all-miniLM-L6-V2-test_case0] PASSED
tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=all-miniLM-L6-V2-test_case1] PASSED
tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=all-miniLM-L6-V2-test_case2] PASSED
tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=all-miniLM-L6-V2-test_case3] PASSED
tests/integration/vector_io/test_vector_io.py::test_insert_chunks[emb=all-miniLM-L6-V2-test_case4] PASSED
========================================================================================================================================================================================================================================================= 7 passed, 2 warnings in 40.33s ==========================================================================================================================================================================================================================================================
```
[//]: # (## Documentation)
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
# What does this PR do?
This is to stay consistent with other APIs.
This change registers files in API, even though there are still no
providers. Removing tests that require a provider existing for a merged
API to enable it in API layer.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
[//]: # (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: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
This PR adds support for NVIDIA's NeMo Customizer API to the Llama Stack
post-training module. The integration enables users to fine-tune models
using NVIDIA's cloud-based customization service through a consistent
Llama Stack interface.
[//]: # (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.*]
Yet to be done
Things pending under this PR:
- [x] Integration of fine-tuned model(new checkpoint) for inference with
nvidia llm distribution
- [x] distribution integration of API
- [x] Add test cases for customizer(In Progress)
- [x] Documentation
```
LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/post_training/test_supervised_fine_tuning.py
============================================================================================================================================================================ test session starts =============================================================================================================================================================================
platform linux -- Python 3.10.0, pytest-8.3.4, pluggy-1.5.0 -- /home/ubuntu/llama-stack/.venv/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.10.0', 'Platform': 'Linux-6.8.0-1021-gcp-x86_64-with-glibc2.35', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'nbval': '0.11.0', 'metadata': '3.1.1', 'anyio': '4.8.0', 'html': '4.1.1', 'asyncio': '0.25.3'}}
rootdir: /home/ubuntu/llama-stack
configfile: pyproject.toml
plugins: nbval-0.11.0, metadata-3.1.1, anyio-4.8.0, html-4.1.1, asyncio-0.25.3
asyncio: mode=strict, asyncio_default_fixture_loop_scope=None
collected 2 items
tests/client-sdk/post_training/test_supervised_fine_tuning.py::test_post_training_provider_registration[txt=8B] PASSED [ 50%]
tests/client-sdk/post_training/test_supervised_fine_tuning.py::test_list_training_jobs[txt=8B] PASSED [100%]
======================================================================================================================================================================== 2 passed, 1 warning in 0.10s ========================================================================================================================================================================
```
cc: @mattf @dglogo @sumitb
---------
Co-authored-by: Ubuntu <ubuntu@llama-stack-customizer-dev-inst-2tx95fyisatvlic4we8hidx5tfj.us-central1-a.c.brevdevprod.internal>
# What does this PR do?
This PR updates the sqlite-vec database calls to be non-blocking. Note
that each operation creates a new connection, which incurs some
performance overhead but is reasonable given [SQLite's threading and
connections constraints](https://www.sqlite.org/threadsafe.html).
Summary of changes:
- Refactored `SQLiteVecIndex` class to store database path instead of
connection object
- Added `_create_sqlite_connection()` helper function to create
connections on demand
- Ensured proper connection closure in all database operations
- Fixed test fixtures to use a file-based SQLite database for
thread-safety
- Updated the `SQLiteVecVectorIOAdapter` class to handle per-operation
connections
This PR helps chip away at
https://github.com/meta-llama/llama-stack/issues/1489
## Test Plan
sqlite-vec unit tests passed locally as well as a test script using the
client as a library.
## Misc
FYI @varshaprasad96 @kevincogan
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
# What does this PR do?
**What**
Instead of adhoc creating a vectordb and chunking when documents ae sent
as an attachment to agent turn, we directly pass raw text from document
into messages to model for user context, and let model perform
summarization directly.
This removes the magic behaviour, and yields better performance than
existing approach.
**Improved Performance**
- RAG lifecycle notebook
- Model: 0.3 factuality score
- (+ websearch) Agent: 0.44 factuality score
- (+ vector db) Agent: 0.3 factuality score
- (+ raw context) Agent: 0.6 factuality score
Closes https://github.com/meta-llama/llama-stack/issues/1478
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- [NEW] added section in RAG lifecycle notebook shows better performance
<img width="840" alt="image"
src="https://github.com/user-attachments/assets/a0c4e816-809a-41c0-9124-89825983e3f5"
/>
[//]: # (## Documentation)
# What does this PR do?
1) Uses otel compatible id generation for stack
2) Stack starts returning trace id info in the header of response
3) We inject the same trace id that we have into otel in order to force
it to use our trace ids.
## Test Plan
```
curl -i --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}'
HTTP/1.1 200 OK
date: Fri, 21 Mar 2025 21:51:19 GMT
server: uvicorn
content-length: 1712
content-type: application/json
x-trace-id: 595101ede31ece116ebe35b26d67e8cf
{"metrics":[{"metric":"prompt_tokens","value":10,"unit":null},{"metric":"completion_tokens","value":320,"unit":null},{"metric":"total_tokens","value":330,"unit":null}],"completion_message":{"role":"assistant","content":"Humans live on the planet Earth, specifically on its landmasses and in its oceans. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica ( temporary residents, mostly scientists and researchers)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near coastlines, rivers, or other bodies of water.\n4. **Rural areas:** Some humans live in rural areas, such as villages, farms, and countryside.\n5. **Islands:** Humans inhabit many islands around the world, including tropical islands, island nations, and islands in the Arctic and Antarctic regions.\n6. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n7. **Space:** A small number of humans have lived in space, including astronauts on the International Space Station and those who have visited the Moon.\n\nIn terms of specific environments, humans live in a wide range of ecosystems, including:\n\n* Deserts\n* Forests\n* Grasslands\n* Mountains\n* Oceans\n* Rivers\n* Tundras\n* Wetlands\n\nOverall, humans are incredibly adaptable and can be found living in almost every corner of the globe.","stop_reason":"end_of_turn","tool_calls":[]},"logprobs":null}
```
Same trace id in Jaeger and sqlite:
# What does this PR do?
## Test Plan
LLAMA_STACK_CONFIG=dev pytest -s -v
tests/integration/agents/test_agents.py::test_custom_tool
--safety-shield meta-llama/Llama-Guard-3-8B --text-model
accounts/fireworks/models/llama-v3p1-8b-instruct
and verify trace in jaeger UI
https://llama-stack.readthedocs.io/en/latest/building_applications/telemetry.html#
# What does this PR do?
- We cannot directly return a literal type
> Note: this is not final jobs API change
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
<img width="837" alt="image"
src="https://github.com/user-attachments/assets/18a17561-35f9-443d-987d-54afdd6ff40c"
/>
[//]: # (## Documentation)
Required to startup a distribution with prompt guard
Closes: #1723
## Test Plan
distribution starts with patch applied
Signed-off-by: Derek Higgins <derekh@redhat.com>
# What does this PR do?
Since we now start recording and exporting metrics, we no longer can use
single OTEL endpoint to export both traces and metrics. This PR adds two
sinks: OTEL_TRACE and OTEL_METRIC to be able to selectively enable the
exporters.
## Test Plan
Start server with OTEL_TRACE as sink and verify traces show up in jaeger
# What does this PR do?
Clean up mypy violations for inline::{telemetry,tool_runtime,vector_io}.
This also makes API accept a tool call result without any content (like
RAG tool already may produce).
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
