# 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>
Add the content to use AMD GPU as the vLLM server. Split the original
part to two sub chapters,
1. AMD vLLM server
2. NVIDIA vLLM server (orignal)
# What does this PR do?
[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.*]
[//]: # (## Documentation)
---------
Signed-off-by: Alex He <alehe@amd.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
# 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
```
# What does this PR do?
* Fix location of `run.yaml` relative to the cloned llama stack
repository
* Drop `-it` from `docker run` commands as its not needed running
services
## Test Plan
* Verified running the llama stack following updated instruction
CC: @ashwinb
Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.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?
## 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?
This is to avoid errors like the following when running inference
integration tests:
```
ERROR tests/integration/inference/test_text_inference.py::test_text_completion_stop_sequence[txt=8B-inference:completion:stop_sequence] - llama_stack.distribution.stack.EnvVarError: Environment variable 'VLLM_URL' not set or empty at providers.inference[0].config.url
```
It's also good to have a default, which is consistent with vLLM API
server.
## Test Plan
Integration tests can run without the error above.
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
## What does this PR do?
fix the template to make it compatible with the latest dataset and eval
api change
## test
run `llama stack run
llama_stack/templates/experimental-post-training/run.yaml` and spin up
the llama stack server successfully
# What does this PR do?
In this PR, we added a new eval open benchmark IfEval based on paper
https://arxiv.org/abs/2311.07911 to measure the model capability of
instruction following.
## Test Plan
spin up a llama stack server with open-benchmark template
run `llama-stack-client --endpoint xxx eval run-benchmark
"meta-reference-ifeval" --model-id "meta-llama/Llama-3.3-70B-Instruct"
--output-dir "/home/markchen1015/" --num-examples 20` on client side and
get the eval aggregate results
# What does this PR do?
DocVQA asks model to look a a picture, then answer a question given in
text, with a text answer by text information in the picture. these
questions often require understanding of relative positions of texts
within the picture.
original dataset is defined in the "Task1" of
https://www.docvqa.org/datasets
## Test Plan
setup llama server with
```
llama stack run ./llama_stack/templates/open-benchmark/run.yaml
```
then send traffic:
```
llama-stack-client eval run-benchmark "meta-reference-docvqa" --model-id meta-llama/Llama-3.3-70B-Instruct --output-dir /tmp/gpqa --num-examples 200
```
## What does this PR do?
open-benchmark templated is broken after the datasets api refactor due
to 2 reasons
- provider_id and provider_resource_id are no longer needed
- the type in run.yaml will be resolved as dict
this PR is to fix the above 2 issues
## Test
spin up a llama stack server successfully with llama stack run
`llama_stack/templates/open-benchmark/run.yaml`
# What does this PR do?
Add the option to not verify SSL certificates for the remote-vllm
provider. This allows llama stack server to talk to remote LLMs which
have self-signed certificates
Partially addresses #1545
# What does this PR do?
create a new dataset BFCL_v3 from
https://gorilla.cs.berkeley.edu/blogs/13_bfcl_v3_multi_turn.html
overall each question asks the model to perform a task described in
natural language, and additionally a set of available functions and
their schema are given for the model to choose from. the model is
required to write the function call form including function name and
parameters , to achieve the stated purpose. the results are validated
against provided ground truth, to make sure that the generated function
call and the ground truth function call are syntactically and
semantically equivalent, by checking their AST .
## Test Plan
start server by
```
llama stack run ./llama_stack/templates/ollama/run.yaml
```
then send traffic
```
llama-stack-client eval run-benchmark "bfcl" --model-id meta-llama/Llama-3.2-3B-Instruct --output-dir /tmp/gpqa --num-examples 2
```
[//]: # (## Documentation)
# What does this PR do?
- Fix issue w/ passthrough provider
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
llama stack run
[//]: # (## Documentation)
# What does this PR do?
- fix precommit
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
CI
[//]: # (## Documentation)
## What does this PR do?
As title, add codegen for open-benchmark template
## test
checked the new generated run.yaml file and it's identical before and
after the change
Also add small improvement to together template so that missing
TOGETHER_API_KEY won't crash the server which is the consistent user
experience as other remote providers
# What does this PR do?
remove Llama-3.2-1B-Instruct for fireworks as its no longer appears to
be hosted on website.
## Test Plan
python distro_codegen.py
## What does this PR do?
Created a new math_500 open-benchmark based on OpenAI's [Let's Verify
Step by Step](https://arxiv.org/abs/2305.20050) paper and hugging face's
[HuggingFaceH4/MATH-500](https://huggingface.co/datasets/HuggingFaceH4/MATH-500)
dataset.
The challenge part of this benchmark is to parse the generated and
expected answer and verify if they are same. For the parsing part, we
refer to [Minerva: Solving Quantitative Reasoning Problems with Language
Models](https://research.google/blog/minerva-solving-quantitative-reasoning-problems-with-language-models/).
To simply the parse logic, as the next step, we plan to also refer to
what [simple-eval](https://github.com/openai/simple-evals) is doing,
using llm as judge to check if the generated answer matches the expected
answer or not
## Test Plan
on sever side, spin up a server with open-benchmark template `llama
stack run llama_stack/templates/open-benchamrk/run.yaml`
on client side, issue an open benchmark eval request `llama-stack-client
--endpoint xxx eval run-benchmark "meta-reference-math-500" --model-id
"meta-llama/Llama-3.3-70B-Instruct" --output-dir "/home/markchen1015/"
--num-examples 20` and get ther aggregated eval results
<img width="238" alt="Screenshot 2025-03-10 at 7 57 04 PM"
src="https://github.com/user-attachments/assets/2c9da042-3b70-470e-a7c4-69f4cc24d1fb"
/>
check the generated answer and the related scoring and they make sense
This is unfortunate because `sqlite-vec` seems promising. But its PIP
package is not quite complete. It does not have binary for arm64 (I
think, or maybe it even lacks 64 bit builds?) which results in the arm64
container resulting in
```
File "/usr/local/lib/python3.10/site-packages/sqlite_vec/init.py", line 17, in load
conn.load_extension(loadable_path())
sqlite3.OperationalError: /usr/local/lib/python3.10/site-packages/sqlite_vec/vec0.so: wrong ELF class: ELFCLASS32
```
To get around I tried to install from source via `uv pip install
sqlite-vec --no-binary=sqlite-vec` however it even lacks a source
distribution which makes that impossible.
## Test Plan
Build the container locally using:
```bash
LLAMA_STACK_DIR=. llama stack build --template ollama --image-type container
```
Run the container as:
```
podman run --privileged -it -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env OLLAMA_URL=http://host.containers.internal:11434 \
-v ~/local/llama-stack:/app/llama-stack-source
localhost/distribution-ollama:dev --port $LLAMA_STACK_PORT
```
Verify the container starts up correctly. Without this patch, it would
encounter the ELFCLASS32 error.
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
It should changed in this pr
https://github.com/meta-llama/llama-stack/pull/1190/files#diff-53e3f35ced54ee5e57dc8b0d3b04770ed84f2f6434c6f492f42569b3c2810ecd
[//]: # (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: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
# What does this PR do?
This PR updates the inline vLLM inference provider in several
significant ways:
* Models are now attached at run time to instances of the provider via
the `.../models` API instead of hard-coding the model's full name into
the provider's YAML configuration.
* The provider supports models that are not Meta Llama models. Any model
that vLLM supports can be loaded by passing Huggingface coordinates in
the "provider_model_id" field. Custom fine-tuned versions of Meta Llama
models can be loaded by specifying a path on local disk in the
"provider_model_id".
* To implement full chat completions support, including tool calling and
constrained decoding, the provider now routes the `chat_completions` API
to a captive (i.e. called directly in-process, not via HTTPS) instance
of vLLM's OpenAI-compatible server .
* The `logprobs` parameter and completions API are also working.
## Test Plan
Existing tests in
`llama_stack/providers/tests/inference/test_text_inference.py` have good
coverage of the new functionality. These tests can be invoked as
follows:
```
cd llama-stack && pytest \
-vvv \
llama_stack/providers/tests/inference/test_text_inference.py \
--providers inference=vllm \
--inference-model meta-llama/Llama-3.2-3B-Instruct
====================================== test session starts ======================================
platform linux -- Python 3.12.8, pytest-8.3.4, pluggy-1.5.0 -- /mnt/datadisk1/freiss/llama/env/bin/python3.12
cachedir: .pytest_cache
metadata: {'Python': '3.12.8', 'Platform': 'Linux-6.8.0-1016-ibm-x86_64-with-glibc2.39', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'anyio': '4.8.0', 'html': '4.1.1', 'metadata': '3.1.1', 'asyncio': '0.25.2'}, 'JAVA_HOME': '/usr/lib/jvm/java-8-openjdk-amd64'}
rootdir: /mnt/datadisk1/freiss/llama/llama-stack
configfile: pyproject.toml
plugins: anyio-4.8.0, html-4.1.1, metadata-3.1.1, asyncio-0.25.2
asyncio: mode=Mode.STRICT, asyncio_default_fixture_loop_scope=None
collected 9 items
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[-vllm] PASSED [ 11%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-vllm] PASSED [ 22%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_logprobs[-vllm] PASSED [ 33%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-vllm] PASSED [ 44%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[-vllm] PASSED [ 55%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[-vllm] PASSED [ 66%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[-vllm] PASSED [ 77%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[-vllm] PASSED [ 88%]
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[-vllm] PASSED [100%]
=========================== 9 passed, 13 warnings in 97.18s (0:01:37) ===========================
```
## Sources
## Before submitting
- [X] Ran pre-commit to handle lint / formatting issues.
- [X] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
---------
Co-authored-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
All of the tests from `llama_stack/providers/tests/` are now moved to
`tests/integration`.
I converted the `tools`, `scoring` and `datasetio` tests to use API.
However, `eval` and `post_training` proved to be a bit challenging to
leaving those. I think `post_training` should be relatively
straightforward also.
As part of this, I noticed that `wolfram_alpha` tool wasn't added to
some of our commonly used distros so I added it. I am going to remove a
lot of code duplication from distros next so while this looks like a
one-off right now, it will go away and be there uniformly for all
distros.
# What does this PR do?
[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.*]
[//]: # (## Documentation)
---------
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
# What does this PR do?
We want to bundle a bunch of (typically remote) providers in a distro
template and be able to configure them "on the fly" via environment
variables. So far, we have been able to do this with simple env var
replacements. However, sometimes you want to only conditionally enable
providers (because the relevant remote services may not be alive, or
relevant.) This was not possible until now.
To aid this, we add a simple (bash-like) env var replacement
enhancement: `${env.FOO+bar}` evaluates to `bar` if the variable is SET
and evaluates to empty string if it is not. On top of that, we update
our main resolver to ignore any provider whose ID is null.
This allows using the distro like this:
```bash
llama stack run dev --env CHROMADB_URL=http://localhost:6001 --env ENABLE_CHROMADB=1
```
when only Chroma is UP. This disables the other `pgvector` provider in
the run configuration.
## Test Plan
Hard code `chromadb` as the vector io provider inside
`test_vector_io.py` and run:
```bash
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -s -v tests/client-sdk/vector_io/ --embedding-model all-MiniLM-L6-v2
```
# What does this PR do?
[Provide a short summary of what this PR does and why. Link to relevant
issues if applicable.]
Since released the `--downloaded` option, so update the related
documents.
[//]: # (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: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
# What does this PR do?
[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.*]
[//]: # (## Documentation)
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: reidliu <reid201711@gmail.com>
Each model known to the system has two identifiers:
- the `provider_resource_id` (what the provider calls it) -- e.g.,
`accounts/fireworks/models/llama-v3p1-8b-instruct`
- the `identifier` (`model_id`) under which it is registered and gets
routed to the appropriate provider.
We have so far used the HuggingFace repo alias as the standardized
identifier you can use to refer to the model. So in the above example,
we'd use `meta-llama/Llama-3.1-8B-Instruct` as the name under which it
gets registered. This makes it convenient for users to refer to these
models across providers.
However, we forgot to register the _actual_ provider model ID also. You
should be able to route via `provider_resource_id` also, of course.
This change fixes this (somewhat grave) omission.
*Note*: this change is additive -- more aliases work now compared to
before.
## Test Plan
Run the following for distro=(ollama fireworks together)
```
LLAMA_STACK_CONFIG=$distro \
pytest -s -v tests/client-sdk/inference/test_text_inference.py \
--inference-model=meta-llama/Llama-3.1-8B-Instruct --vision-inference-model=""
```
Groq has never supported raw completions anyhow. So this makes it easier
to switch it to LiteLLM. All our test suite passes.
I also updated all the openai-compat providers so they work with api
keys passed from headers. `provider_data`
## Test Plan
```bash
LLAMA_STACK_CONFIG=groq \
pytest -s -v tests/client-sdk/inference/test_text_inference.py \
--inference-model=groq/llama-3.3-70b-versatile --vision-inference-model=""
```
Also tested (openai, anthropic, gemini) providers. No regressions.
# What does this PR do?
Model context protocol (MCP) allows for remote tools to be connected
with Agents. The current Ollama provider does not support it. This PR
adds necessary code changes to ensure that the integration between
Ollama backend and MCP works.
This PR is an extension of #816 for Ollama.
## 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. Run llama-stack server with the command:
```
llama stack build --template ollama --image-type conda
llama stack run ./templates/ollama/run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env OLLAMA_URL=http://localhost:11434
```
2. Run the sample client agent with MCP tool:
```
from llama_stack_client.lib.agents.agent import Agent
from llama_stack_client.lib.agents.event_logger import EventLogger
from llama_stack_client.types.agent_create_params import AgentConfig
from llama_stack_client.types.shared_params.url import URL
from llama_stack_client import LlamaStackClient
from termcolor import cprint
## Start the local MCP server
# git clone https://github.com/modelcontextprotocol/python-sdk
# Follow instructions to get the env ready
# cd examples/servers/simple-tool
# uv run mcp-simple-tool --transport sse --port 8000
# Connect to the llama stack server
base_url="http://localhost:8321"
model_id="meta-llama/Llama-3.2-3B-Instruct"
client = LlamaStackClient(base_url=base_url)
# Register MCP tools
client.toolgroups.register(
toolgroup_id="mcp::filesystem",
provider_id="model-context-protocol",
mcp_endpoint=URL(uri="http://localhost:8000/sse"))
# Define an agent with MCP toolgroup
agent_config = AgentConfig(
model=model_id,
instructions="You are a helpful assistant",
toolgroups=["mcp::filesystem"],
input_shields=[],
output_shields=[],
enable_session_persistence=False,
)
agent = Agent(client, agent_config)
user_prompts = [
"Fetch content from https://www.google.com and print the response"
]
# Run a session with the agent
session_id = agent.create_session("test-session")
for prompt in user_prompts:
cprint(f"User> {prompt}", "green")
response = agent.create_turn(
messages=[
{
"role": "user",
"content": prompt,
}
],
session_id=session_id,
)
for log in EventLogger().log(response):
log.print()
```
# Documentation
The file docs/source/distributions/self_hosted_distro/ollama.md is
updated to indicate the MCP tool runtime availability.
Signed-off-by: Shreyanand <shanand@redhat.com>
