mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-22 20:43:59 +00:00
b76bef169c
# 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.
141 lines
3.7 KiB
YAML
141 lines
3.7 KiB
YAML
version: '2'
|
|
image_name: nvidia
|
|
conda_env: nvidia
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- memory
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
providers:
|
|
inference:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
url: https://integrate.api.nvidia.com
|
|
api_key: ${env.NVIDIA_API_KEY}
|
|
memory:
|
|
- 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: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config: {}
|
|
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:
|
|
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
|
|
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: {}
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config: {}
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config: {}
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
config: {}
|
|
- provider_id: llm-as-judge
|
|
provider_type: inline::llm-as-judge
|
|
config: {}
|
|
- provider_id: braintrust
|
|
provider_type: inline::braintrust
|
|
config:
|
|
openai_api_key: ${env.OPENAI_API_KEY:}
|
|
tool_runtime:
|
|
- provider_id: brave-search
|
|
provider_type: remote::brave-search
|
|
config:
|
|
api_key: ${env.BRAVE_SEARCH_API_KEY:}
|
|
max_results: 3
|
|
- provider_id: tavily-search
|
|
provider_type: remote::tavily-search
|
|
config:
|
|
api_key: ${env.TAVILY_SEARCH_API_KEY:}
|
|
max_results: 3
|
|
- provider_id: code-interpreter
|
|
provider_type: inline::code-interpreter
|
|
config: {}
|
|
- provider_id: memory-runtime
|
|
provider_type: inline::memory-runtime
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3-8B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama3-8b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3-70B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama3-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-8B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.1-8b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-70B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.1-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.1-405b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-1B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-1b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-3B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-3b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-11b-vision-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-90b-vision-instruct
|
|
model_type: llm
|
|
shields: []
|
|
memory_banks: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
eval_tasks: []
|
|
tool_groups: []
|