# What does this PR do?
The goal of this PR is code base modernization.
Schema reflection code needed a minor adjustment to handle UnionTypes
and collections.abc.AsyncIterator. (Both are preferred for latest Python
releases.)
Note to reviewers: almost all changes here are automatically generated
by pyupgrade. Some additional unused imports were cleaned up. The only
change worth of note can be found under `docs/openapi_generator` and
`llama_stack/strong_typing/schema.py` where reflection code was updated
to deal with "newer" types.
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
# What does this PR do?
Providers that live outside of the llama-stack codebase are now
supported.
A new property `external_providers_dir` has been added to the main
config and can be configured as follow:
```
external_providers_dir: /etc/llama-stack/providers.d/
```
Where the expected structure is:
```
providers.d/
inference/
custom_ollama.yaml
vllm.yaml
vector_io/
qdrant.yaml
```
Where `custom_ollama.yaml` is:
```
adapter:
adapter_type: custom_ollama
pip_packages: ["ollama", "aiohttp"]
config_class: llama_stack_ollama_provider.config.OllamaImplConfig
module: llama_stack_ollama_provider
api_dependencies: []
optional_api_dependencies: []
```
Obviously the package must be installed on the system, here is the
`llama_stack_ollama_provider` example:
```
$ uv pip show llama-stack-ollama-provider
Using Python 3.10.16 environment at: /Users/leseb/Documents/AI/llama-stack/.venv
Name: llama-stack-ollama-provider
Version: 0.1.0
Location: /Users/leseb/Documents/AI/llama-stack/.venv/lib/python3.10/site-packages
Editable project location: /private/var/folders/mq/rnm5w_7s2d3fxmtkx02knvhm0000gn/T/tmp.ZBHU5Ezxg4/ollama/llama-stack-ollama-provider
Requires:
Required-by:
```
Closes: https://github.com/meta-llama/llama-stack/issues/658
Signed-off-by: Sébastien Han <seb@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?
currently the `inspect` API for providers is really a `list` API. Create
a new `providers` API which has a GET `providers/{provider_id}` inspect
API
which returns "user friendly" configuration to the end user. Also add a
GET `/providers` endpoint which returns the list of providers as
`inspect/providers` does today.
This API follows CRUD and is more intuitive/RESTful.
This work is part of the RFC at
https://github.com/meta-llama/llama-stack/pull/1359
sensitive fields are redacted using `redact_sensetive_fields` on the
server side before returning a response:
<img width="456" alt="Screenshot 2025-03-13 at 4 40 21 PM"
src="https://github.com/user-attachments/assets/9465c221-2a26-42f8-a08a-6ac4a9fecce8"
/>
## Test Plan
using https://github.com/meta-llama/llama-stack-client-python/pull/181 a
user is able to to run the following:
`llama stack build --template ollama --image-type venv`
`llama stack run --image-type venv
~/.llama/distributions/ollama/ollama-run.yaml`
`llama-stack-client providers inspect ollama`
<img width="378" alt="Screenshot 2025-03-13 at 4 39 35 PM"
src="https://github.com/user-attachments/assets/8273d05d-8bc3-44c6-9e4b-ef95e48d5466"
/>
also, was able to run the new test_list integration test locally with
ollama:
<img width="1509" alt="Screenshot 2025-03-13 at 11 03 40 AM"
src="https://github.com/user-attachments/assets/9b9db166-f02f-45b0-86a4-306d85149bc8"
/>
Signed-off-by: Charlie Doern <cdoern@redhat.com>
# What does this PR do?
This PR adds back the changes in #1300 which were reverted in #1476 .
It also adds logic to preserve context variables across asyncio
boundary. this is needed with the library client since the async
generator logic yields control to code outside the event loop, and on
resuming, does not have the same context as before and this requires
preserving the context vars.
address #1477
## Test Plan
```
curl --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
}' | jq .
{
"metrics": [
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549084Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549449Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 369,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549457Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 379,
"unit": "tokens"
}
],
"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 those in the Pacific, Indian, and Atlantic Oceans.\n6. **Mountains and highlands:** Humans live in mountainous regions, such as the Himalayas, the Andes, and the Rocky Mountains.\n7. **Deserts:** Some humans live in desert regions, such as the Sahara, the Mojave, and the Atacama.\n8. **Coastal areas:** Many humans live in coastal areas, such as beaches, ports, and coastal cities.\n9. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n10. **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\nOverall, humans can be found living in almost every environment on Earth, from the frozen tundra to the hottest deserts, and from the highest mountains to the deepest oceans.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
Orignal repro no longer showing any error:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
client logs:
https://gist.github.com/dineshyv/047c7e87b18a5792aa660e311ea53166
server logs:
https://gist.github.com/dineshyv/97a2174099619e9916c7c490be26e559
# What does this PR do?
This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:
```
INFO 2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
tavily-search
```
Key features include:
- Category-based logging: Loggers can be assigned a category (e.g.,
"core", "server") when programming. The logger can be loaded like
this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
`LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
third-party libraries.
This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.
The formatter uses the rich library which provides nice colors better
stack traces like so:
```
ERROR 2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
│ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown │
│ │
│ 175 │ │ except asyncio.CancelledError: │
│ 176 │ │ │ pass │
│ 177 │ │ finally: │
│ ❱ 178 │ │ │ loop.stop() │
│ 179 │ │
│ 180 │ loop = asyncio.get_running_loop() │
│ 181 │ loop.create_task(shutdown()) │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
UnboundLocalError: local variable 'loop' referenced before assignment
```
Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:
INFO 2025-03-03 21:55:35,928 __main__:380 [server]: apis:
- agents
```
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
# What does this PR do?
Inference router computes the token usage related metrics for all
providers and returns the metrics as part of response and also logs to
telemetry.
## Test Plan
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/fireworks/fireworks-run.yaml
```
curl --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
}' | jq .
{
"metrics": [
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770903Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770916Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 411,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770919Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 421,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world, inhabiting almost every continent, country, and region. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica (research stations only)\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. **Regions:** Humans live in diverse regions, including:\n\t* Deserts (e.g., Sahara, Mojave)\n\t* Forests (e.g., Amazon, Congo)\n\t* Grasslands (e.g., Prairies, Steppes)\n\t* Mountains (e.g., Himalayas, Andes)\n\t* Oceans (e.g., coastal areas, islands)\n\t* Tundras (e.g., Arctic, sub-Arctic)\n4. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near:\n\t* Coastlines\n\t* Rivers\n\t* Lakes\n\t* Mountains\n5. **Rural areas:** Some humans live in rural areas, such as:\n\t* Villages\n\t* Farms\n\t* Countryside\n6. **Islands:** Humans inhabit many islands, including:\n\t* Tropical islands (e.g., Hawaii, Maldives)\n\t* Arctic islands (e.g., Greenland, Iceland)\n\t* Continental islands (e.g., Great Britain, Ireland)\n7. **Extreme environments:** Humans also live in extreme environments, such as:\n\t* High-altitude areas (e.g., Tibet, Andes)\n\t* Low-altitude areas (e.g., Death Valley, Dead Sea)\n\t* Areas with extreme temperatures (e.g., Arctic, Sahara)\n\nOverall, humans have adapted to live in a wide range of environments and ecosystems around the world.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/inference
======================================================================== short test summary info =========================================================================
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-True] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-False] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_non_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
========================================================= 4 failed, 16 passed, 23 xfailed, 17 warnings in 44.36s =========================================================
```
# What does this PR do?
- Modularized `resolve_impls` by extracting helper functions for
validation, sorting, and instantiation.
- Improved readability by introducing `validate_and_prepare_providers`,
`sort_providers_by_dependency`, and `instantiate_providers`.
- Enhanced type safety with explicit type hints (`Tuple`, `Dict`, `Set`,
etc.).
- Fixed potential issues with provider module imports and added error
handling.
- Updated `pyproject.toml` to enforce type checking on `resolver.py`
using `mypy`.
Signed-off-by: Sébastien Han <seb@redhat.com>
- [//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
Run the server.
[//]: # (## Documentation)
Signed-off-by: Sébastien Han <seb@redhat.com>
A self-respecting server needs good observability which starts with
configurable logging. Llama Stack had little until now. This PR adds a
`logcat` facility towards that. Callsites look like:
```python
logcat.debug("inference", f"params to ollama: {params}")
```
- the first parameter is a category. there is a static list of
categories in `llama_stack/logcat.py`
- each category can be associated with a log-level which can be
configured via the `LLAMA_STACK_LOGGING` env var.
- a value `LLAMA_STACK_LOGGING=inference=debug;server=info"` does the
obvious thing. there is a special key called `all` which is an alias for
all categories
## Test Plan
Ran with `LLAMA_STACK_LOGGING="all=debug" llama stack run fireworks` and
saw the following:
Hit it with a client-sdk test case and saw this:
# 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?
- Update `/eval-tasks` to `/benchmarks`
- ⚠️ Remove differentiation between `app` v.s. `benchmark` eval task
config. Now we only have `BenchmarkConfig`. The overloaded `benchmark`
is confusing and do not add any value. Backward compatibility is being
kept as the "type" is not being used anywhere.
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- This change is backward compatible
- Run notebook test with
```
pytest -v -s --nbval-lax ./docs/getting_started.ipynb
pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
<img width="846" alt="image"
src="https://github.com/user-attachments/assets/d2fc06a7-593a-444f-bc1f-10ab9b0c843d"
/>
[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)
---------
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Signed-off-by: Sébastien Han <seb@redhat.com>
Signed-off-by: reidliu <reid201711@gmail.com>
Co-authored-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
Co-authored-by: Ben Browning <ben324@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Reid <61492567+reidliu41@users.noreply.github.com>
Co-authored-by: reidliu <reid201711@gmail.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>
Lint check in main branch is failing. This fixes the lint check after we
moved to ruff in https://github.com/meta-llama/llama-stack/pull/921. We
need to move to a `ruff.toml` file as well as fixing and ignoring some
additional checks.
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.
Third part:
- we need to make `tool_runtime.rag_tool.query_context()` and
`tool_runtime.rag_tool.insert_documents()` methods work smoothly with
complete type safety. To that end, we introduce a sub-resource path
`tool-runtime/rag-tool/` and make changes to the resolver to make things
work.
- the PR updates the agents implementation to directly call these typed
APIs for memory accesses rather than going through the complex, untyped
"invoke_tool" API. the code looks much nicer and simpler (expectedly.)
- there are a number of hacks in the server resolver implementation
still, we will live with some and fix some
Note that we must make sure the client SDKs are able to handle this
subresource complexity also. Stainless has support for subresources, so
this should be possible but beware.
## Test Plan
Our RAG test is sad (doesn't actually test for actual RAG output) but I
verified that the implementation works. I will work on fixing the RAG
test afterwards.
```bash
pytest -s -v tests/agents/test_agents.py -k "rag and together" --safety-shield=meta-llama/Llama-Guard-3-8B
```
See https://github.com/meta-llama/llama-stack/issues/827 for the broader
design.
This is the first part:
- delete other kinds of memory banks (keyvalue, keyword, graph) for now;
we will introduce a keyvalue store API as part of this design but not
use it in the RAG tool yet.
- renaming of the APIs
# 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
### Context
This is the 1st of series PRs that integrate torchtune with llama-stack
as meta reference post-training implementation. For MVP, we will focus
on single device LoRA SFT.
Though this PR is still WIP, we want to get early feedback on the high
level design of this skeleton while still working on several details
### Scope
To limit the scope of this PR, we focus on the skeleton of the
implementation.
**What are included?**
- refine the post-training SFT apis
- skeleton of supervised_fine_tune implementation. We verified that we
can call the supervised_fine_tune API successfully from llama stack
client SDK (client side PR:
https://github.com/meta-llama/llama-stack-client-python/pull/51)
- a very basic single device LoRA training recipe based on torchtune
core components
- parity check with torchtune library and post training api unit test
**What are not includes?**
- implementation of other job management, get training artifacts apis
(separate PR)
- refactor the meta reference inference logic to support eval on
finetuned model (separate PR)
- several necessary functionality in the training recipe such as
logging, validation etc (separate PR)
- interop with telemetry for tracing and metrics logging, currently
temporarily log to local disk (separate PR)
### Testing
**e2e test**
Although we haven't added detailed testing and numerical parity check
with torchtune yet, we did a simple E2E test from client to server
1. setup server with` llama stack build --template
experimental-post-training --image-type conda` and `llama stack run
experimental-post-training `
2. On client, run `llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 post_training
supervised_fine_tune`
3. Training finishes successfully. On server side, get the finetune
checkpoints under output dir. On client side, get the job uuid
server
<img width="1110" alt="Screenshot 2024-12-02 at 5 52 32 PM"
src="https://github.com/user-attachments/assets/b548eb90-7a9b-4edc-a858-ee237cc4361d">
client
<img width="807" alt="Screenshot 2024-12-02 at 5 52 37 PM"
src="https://github.com/user-attachments/assets/1138ffa8-4698-40fa-b190-3d7b99646838">
**parity check**
torchtune dataloader output and llama-stack post training dataloader
output are same
<img width="1116" alt="Screenshot 2024-12-04 at 8 18 46 PM"
src="https://github.com/user-attachments/assets/5e295cdc-4c24-4ea6-82c0-ca96ef1bd6ee">
torchtune LoRA SFT and llama-stack post training LoRA SFT on alpaca
dataset with llama3.2 3B instruct model are numerical match
<img width="860" alt="Screenshot 2024-12-04 at 8 17 01 PM"
src="https://github.com/user-attachments/assets/c05cf0a8-c674-4d2e-9f0a-c5d01b2dca99">
<img width="1049" alt="Screenshot 2024-12-04 at 8 17 06 PM"
src="https://github.com/user-attachments/assets/b911d4e2-e7b1-41a9-b62c-d75529b6d443">
**unit test **
![Uploading Screenshot 2024-12-09 at 1.35.10 PM.png…]()
# What does this PR do?
This PR moves all print statements to use logging. Things changed:
- Had to add `await start_trace("sse_generator")` to server.py to
actually get tracing working. else was not seeing any logs
- If no telemetry provider is provided in the run.yaml, we will write to
stdout
- by default, the logs are going to be in JSON, but we expose an option
to configure to output in a human readable way.
# What does this PR do?
This PR kills the notion of "pure passthrough" remote providers. You
cannot specify a single provider you must specify a whole distribution
(stack) as remote.
This PR also significantly fixes / upgrades testing infrastructure so
you can now test against a remotely hosted stack server by just doing
```bash
pytest -s -v -m remote test_agents.py \
--inference-model=Llama3.1-8B-Instruct --safety-shield=Llama-Guard-3-1B \
--env REMOTE_STACK_URL=http://localhost:5001
```
Also fixed `test_agents_persistence.py` (which was broken) and killed
some deprecated testing functions.
## Test Plan
All the tests.
Splits the meta-reference safety implementation into three distinct providers:
- inline::llama-guard
- inline::prompt-guard
- inline::code-scanner
Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/
(Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.)
* persist registered objects with distribution
* linter fixes
* comment
* use annotate and field discriminator
* workign tests
* donot use global state
* precommit failures fixed
* add back Any
* fix imports
* remove unnecessary changes in ollama
* precommit failures fixed
* make kvstore configurable for dist and rename registry
* add comment about registry list return
* fix linter errors
* use registry to hydrate
* remove debug print
* linter fixes
* remove kvstore.db
* rename distribution_registry_store
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This PR makes several core changes to the developer experience surrounding Llama Stack.
Background: PR #92 introduced the notion of "routing" to the Llama Stack. It introduces three object types: (1) models, (2) shields and (3) memory banks. Each of these objects can be associated with a distinct provider. So you can get model A to be inferenced locally while model B, C can be inference remotely (e.g.)
However, this had a few drawbacks:
you could not address the provider instances -- i.e., if you configured "meta-reference" with a given model, you could not assign an identifier to this instance which you could re-use later.
the above meant that you could not register a "routing_key" (e.g. model) dynamically and say "please use this existing provider I have already configured" for a new model.
the terms "routing_table" and "routing_key" were exposed directly to the user. in my view, this is way too much overhead for a new user (which almost everyone is.) people come to the stack wanting to do ML and encounter a completely unexpected term.
What this PR does: This PR structures the run config with only a single prominent key:
- providers
Providers are instances of configured provider types. Here's an example which shows two instances of the remote::tgi provider which are serving two different models.
providers:
inference:
- provider_id: foo
provider_type: remote::tgi
config: { ... }
- provider_id: bar
provider_type: remote::tgi
config: { ... }
Secondly, the PR adds dynamic registration of { models | shields | memory_banks } to the API surface. The distribution still acts like a "routing table" (as previously) except that it asks the backing providers for a listing of these objects. For example it asks a TGI or Ollama inference adapter what models it is serving. Only the models that are being actually served can be requested by the user for inference. Otherwise, the Stack server will throw an error.
When dynamically registering these objects, you can use the provider IDs shown above. Info about providers can be obtained using the Api.inspect set of endpoints (/providers, /routes, etc.)
The above examples shows the correspondence between inference providers and models registry items. Things work similarly for the safety <=> shields and memory <=> memory_banks pairs.
Registry: This PR also makes it so that Providers need to implement additional methods for registering and listing objects. For example, each Inference provider is now expected to implement the ModelsProtocolPrivate protocol (naming is not great!) which consists of two methods
register_model
list_models
The goal is to inform the provider that a certain model needs to be supported so the provider can make any relevant backend changes if needed (or throw an error if the model cannot be supported.)
There are many other cleanups included some of which are detailed in a follow-up comment.
