phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 06:48:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/llama_stack/templates/nvidia/run.yaml
Charlie Doern e4b040d5cc feat: allow for provider immutability 
being able to update providers means that admins should have the ability to turn this feature off. introduce `immutable` as a field in the Provider class. Defauling to false means all providers can be updated by default, but an admin at runtime can choose to set this to True to disable provider updating

Signed-off-by: Charlie Doern <cdoern@redhat.com>
2025-07-01 10:06:53 -04:00

237 lines
6.7 KiB
YAML
Raw Blame History

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}
immutable: false
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
immutable: false
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}
immutable: false
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
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
immutable: false
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/trace_store.db
immutable: false
eval:
- provider_id: nvidia
provider_type: remote::nvidia
config:
evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
immutable: false
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}
immutable: false
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}
immutable: false
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
immutable: false
tool_runtime:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
immutable: false
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
Reference in a new issue View git blame Copy permalink