mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-18 02:42:31 +00:00
5bb3817c49
# What does this PR do? The `nvidia` distro was previously collapsed into the `starter` distro. However, the `nvidia` distro was setup specifically to use NVIDIA NeMo microservices as providers for all APIs and not just inference, which means it was doing quite a bit more than what the `starter` distro covers today. We should work with our friends at NVIDIA to determine the best place to maintain this distro long-term, but for now this restores the `nvidia` distro and its docs back to where they were so that things continue to work for their users. ## Test Plan I ensure the `nvidia` distro could build, and run at least to the point of complaining that I didn't provide the necessary API keys. ``` uv run llama stack build --template nvidia --image-type venv uv run llama stack run llama_stack/templates/nvidia/run.yaml ``` I also made sure the docs website built and looks reasonable, with the `nvidia` distro docs at the same URL it was previously (because it has incoming links from official NVIDIA NeMo docs, among other places). ``` uv run --group docs sphinx-autobuild docs/source docs/build/html --write-all ``` Signed-off-by: Ben Browning <bbrownin@redhat.com>
226 lines
6.6 KiB
YAML
226 lines
6.6 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:=}
|
|
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
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: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/agents_store.db
|
|
responses_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
|
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/trace_store.db
|
|
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
|
eval:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
config:
|
|
evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
|
|
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: 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}
|
|
datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
|
|
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
|
|
inference_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: meta/llama3-8b-instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama3-8b-instruct
|
|
model_type: llm
|
|
- 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/llama3-70b-instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama3-70b-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-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-3.1-8B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.1-8b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta/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-3.1-70B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.1-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta/llama-3.1-405b-instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.1-405b-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-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-3.2-1B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-1b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta/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-3.2-3B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-3b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta/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-3.2-11B-Vision-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-11b-vision-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta/llama-3.2-90b-vision-instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.2-90b-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
|
|
- metadata: {}
|
|
model_id: meta/llama-3.3-70b-instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.3-70b-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.3-70B-Instruct
|
|
provider_id: nvidia
|
|
provider_model_id: meta/llama-3.3-70b-instruct
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 2048
|
|
context_length: 8192
|
|
model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
|
|
provider_id: nvidia
|
|
provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
|
|
model_type: embedding
|
|
- metadata:
|
|
embedding_dimension: 1024
|
|
context_length: 512
|
|
model_id: nvidia/nv-embedqa-e5-v5
|
|
provider_id: nvidia
|
|
provider_model_id: nvidia/nv-embedqa-e5-v5
|
|
model_type: embedding
|
|
- metadata:
|
|
embedding_dimension: 4096
|
|
context_length: 512
|
|
model_id: nvidia/nv-embedqa-mistral-7b-v2
|
|
provider_id: nvidia
|
|
provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
|
|
model_type: embedding
|
|
- metadata:
|
|
embedding_dimension: 1024
|
|
context_length: 512
|
|
model_id: snowflake/arctic-embed-l
|
|
provider_id: nvidia
|
|
provider_model_id: snowflake/arctic-embed-l
|
|
model_type: embedding
|
|
shields: []
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|