# 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?
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?
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?
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
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.
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>
# What does this PR do?
This PR introduces more non-llama model support to llama stack.
Providers introduced: openai, anthropic and gemini. All of these
providers use essentially the same piece of code -- the implementation
works via the `litellm` library.
We will expose only specific models for providers we enable making sure
they all work well and pass tests. This setup (instead of automatically
enabling _all_ providers and models allowed by LiteLLM) ensures we can
also perform any needed prompt tuning on a per-model basis as needed
(just like we do it for llama models.)
## Test Plan
```bash
#!/bin/bash
args=("$@")
for model in openai/gpt-4o anthropic/claude-3-5-sonnet-latest gemini/gemini-1.5-flash; do
LLAMA_STACK_CONFIG=dev pytest -s -v tests/client-sdk/inference/test_text_inference.py \
--embedding-model=all-MiniLM-L6-v2 \
--vision-inference-model="" \
--inference-model=$model "${args[@]}"
done
```
# What does this PR do?
Merges the two "files" field for codegen check. This also fixes the
broken main branch CI build.
## Test Plan
```
Distribution Template Codegen............................................Passed
- hook id: distro-codegen
- duration: 367.44s
```
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
Create a distribution template using Groq as inference provider.
Link to issue: https://github.com/meta-llama/llama-stack/issues/958
## Test Plan
Run `python llama_stack/scripts/distro_codegen.py` to generate run.yaml
and build.yaml
Test the newly created template by running
`llama stack build --template <template-name>`
`llama stack run <template-name>`
Embedding models are tiny and can be pulled on-demand. Let's do that so
the user doesn't have to do "yet another thing" to get themselves set
up.
Thanks @hardikjshah for the suggestion.
Also fixed a build dependency miss (TODO: distro_codegen needs to
actually check that the build template contains all providers mentioned
for the run.yaml file)
## Test Plan
First run `ollama rm all-minilm:latest`.
Run `llama stack build --template ollama && llama stack run ollama --env
INFERENCE_MODEL=llama3.2:3b-instruct-fp16`. See that it outputs a
"Pulling embedding model `all-minilm:latest`" output and the stack
starts up correctly. Verify that `ollama list` shows the model is
correctly downloaded.
# What does this PR do?
Catches docs up to source with:
```
python llama_stack/scripts/distro_codegen.py
```
[//]: # (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.*]
Manually checked
```
sphinx-autobuild docs/source build/html
```
[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)
# What does this PR do?
- we no longer have meta-reference as memory provider, update cerebras
template
## Test Plan
```
python llama_stack/scripts/distro_codegen.py
```
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] 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.
# What does this PR do?
- fix cerebras template
## Test Plan
```
llama stack build --template cerebras --image-type conda
llama stack run cerebras
LLAMA_STACK_BASE_URL="http://localhost:5000" pytest -v tests/client-sdk/ --html=report.html --self-contained-html
```
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] 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.
# What does this PR do?
- fixes to nvidia inference provider to account for strategy update
- update nvidia templates
## Test Plan
```
llama stack run ./llama_stack/templates/nvidia/run.yaml --port 5000
LLAMA_STACK_BASE_URL="http://localhost:5000" pytest -v tests/client-sdk/inference/test_inference.py --html=report.html --self-contained-html
```
<img width="1288" alt="image"
src="https://github.com/user-attachments/assets/d20f9aea-525e-47de-a5be-586e022e0d55"
/>
**NOTE**
- vision inference broken
- tool calling broken
- /completion broken
cc @mattf @cdgamarose-nv for improving NVIDIA inference adapter
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] 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.
Addressed comment
https://github.com/meta-llama/llama-stack/pull/723#issuecomment-2581902075.
cc @yanxi0830
I am not 100% sure if the diff is correct though but this is the result
of running `python llama_stack/scripts/distro_codegen.py`.
---------
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
# What does this PR do?
PR #639 introduced the notion of Tools API and ability to invoke tools
through API just as any resource. This PR changes the Agents to start
using the Tools API to invoke tools. Major changes include:
1) Ability to specify tool groups with AgentConfig
2) Agent gets the corresponding tool definitions for the specified tools
and pass along to the model
3) Attachements are now named as Documents and their behavior is mostly
unchanged from user perspective
4) You can specify args that can be injected to a tool call through
Agent config. This is especially useful in case of memory tool, where
you want the tool to operate on a specific memory bank.
5) You can also register tool groups with args, which lets the agent
inject these as well into the tool call.
6) All tests have been migrated to use new tools API and fixtures
including client SDK tests
7) Telemetry just works with tools API because of our trace protocol
decorator
## Test Plan
```
pytest -s -v -k fireworks llama_stack/providers/tests/agents/test_agents.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
pytest -s -v -k together llama_stack/providers/tests/tools/test_tools.py \
--safety-shield=meta-llama/Llama-Guard-3-8B \
--inference-model=meta-llama/Llama-3.1-8B-Instruct
LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py
```
run.yaml:
https://gist.github.com/dineshyv/0365845ad325e1c2cab755788ccc5994
Notebook:
https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d?usp=sharing
# What does this PR do?
- add llama3.3 model for together
- fix fireworks distro_codegen
```
python llama_stack/scripts/distro_codegen.py
```
## Test Plan
<img width="1132" alt="image"
src="https://github.com/user-attachments/assets/bf94b933-9200-4e73-878e-d1a95d450a88"
/>
**Tests**
```
pytest -v -s -k "together" --inference-model="meta-llama/Llama-3.3-70B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py
```
<img width="1139" alt="image"
src="https://github.com/user-attachments/assets/407dc98b-8de3-4841-8cb1-75e4b5128544"
/>
## Sources
Please link relevant resources if necessary.
## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] 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.
## What does this PR do?
In this PR, we refactor the meta reference inference logic to support
- load the model during registering model instead of during spinning up
server
- support inference finetuned model checkpoint on top of native llama
model
## Why need these changes
To solve the existing pain points that
- user cannot lazy load the model and hot switch the inference
checkpoint after spinning up the server
- this blocks us doing inference and eval on the same sever for a
finetuned checkpoint after post training
- user cannot do inference on a finetuned checkpoint on top of native
llama models
## Expect user experience change
- The inference model won't be loaded when spinning up server. Instead,
it will be loaded during register model. If user add the model as models
resource in run.yaml, it will be registered and loaded automatically
when starting server. There is an optional flag 'skip_initialize' in
model metadata to skip model loading during registration.
- There is an optional flag 'llama_model' in model metadata to identify
the base model of the Model class for validation and initialize model
arch. model identifier no longer needs to be a native llama model
- the default inference model name updates from
'meta-llama/Llama-3.2-3B-Instruct' to 'Llama3.2-3B-Instruct'
- It aligns with the checkpoint folder name after running 'llama model
download'
- It aligns with the descriptor name defined in llama-models SKU list
bf5b0c4fe7/models/datatypes.py (L95)
## test
run python llama_stack/scripts/distro_codegen.py
**run unit test**
- torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.1-8B-Instruct"
./llama_stack/providers/tests/inference/test_text_inference.py
- torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.1-8B-Instruct"
./llama_stack/providers/tests/inference/test_model_registration.py
**test post training experience**
on server side run: llama stack run
llama_stack/templates/experimental-post-training/run.yaml
server is spinning up without model loaded
<img width="812" alt="Screenshot 2024-12-17 at 1 24 50 PM"
src="https://github.com/user-attachments/assets/ce1f606b-3b6f-452f-b48e-b3761ffd90f3"
/>
on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 models register
Llama3.2-3B-Instruct
register model successfully and the model is loaded
<img width="1111" alt="Screenshot 2024-12-17 at 1 26 30 PM"
src="https://github.com/user-attachments/assets/56e02131-cf7d-4de5-8f63-fbdcb8c55c26"
/>
<img width="1541" alt="Screenshot 2024-12-17 at 1 26 09 PM"
src="https://github.com/user-attachments/assets/a83255a1-20f5-40a2-af51-55641410a115"
/>
if add "skip_initialize" in metadata, model is registered but isn't
loaded
on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 inference chat-completion
--message "hello, what model are you?"
Inference the model succesfully
<img width="1121" alt="Screenshot 2024-12-17 at 1 27 33 PM"
src="https://github.com/user-attachments/assets/8e708545-3fe7-4a73-8754-1470fa5f1e75"
/>
**test inference experience**
run: llama stack run llama_stack/templates/meta-reference-gpu/run.yaml
model is loaded since the model is in resouce list in run.yaml
<img width="1537" alt="Screenshot 2024-12-17 at 1 30 19 PM"
src="https://github.com/user-attachments/assets/5c8af817-66eb-43f8-bf4c-f5e24b0a12c6"
/>
on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 inference chat-completion
--message "hello, what model are you?"
inference successfully
<img width="1123" alt="Screenshot 2024-12-17 at 1 31 08 PM"
src="https://github.com/user-attachments/assets/471809aa-c65e-46dc-a37e-7094fb857f97"
/>
## inference on a finetuned model
**register a finetuned model that finetuned by post training api
(torchtune)**
- the model is registered and loaded successfully
- the model is shown up in the model list
<img width="974" alt="Screenshot 2024-12-18 at 3 56 33 PM"
src="https://github.com/user-attachments/assets/2994b4f5-4fa9-40c6-acc6-4b971479f3e2"
/>
**run inference**
<img width="977" alt="Screenshot 2024-12-18 at 3 57 59 PM"
src="https://github.com/user-attachments/assets/d117abbc-b2a0-41d8-a028-1a13128787b2"
/>
# What does this PR do?
Adds the sentence transformer provider and the `all-MiniLM-L6-v2`
embedding model to the default models to register in the run.yaml for
all providers.
## Test Plan
llama stack build --template together --image-type conda
llama stack run
~/.llama/distributions/llamastack-together/together-run.yaml
