mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
1a73f8305b
# 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>
109 lines
2.9 KiB
YAML
109 lines
2.9 KiB
YAML
version: '2'
|
|
image_name: nvidia
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- post_training
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
|
|
api_key: ${env.NVIDIA_API_KEY:}
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
|
|
config_id: self-check
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
|
|
safety:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
|
|
config_id: self-check
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
|
|
post_training:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
api_key: ${env.NVIDIA_API_KEY:}
|
|
dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
|
|
project_id: ${env.NVIDIA_PROJECT_ID:test-project}
|
|
customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
|
|
datasetio:
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
config: {}
|
|
tool_runtime:
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: ${env.INFERENCE_MODEL}
|
|
provider_id: nvidia
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: ${env.SAFETY_MODEL}
|
|
provider_id: nvidia
|
|
model_type: llm
|
|
shields:
|
|
- shield_id: ${env.SAFETY_MODEL}
|
|
provider_id: nvidia
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|