phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-19 19:30:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/llama_stack/templates/nvidia/run.yaml
Ashwin Bharambe 04de2f84e9
fix: register provider model name and HF alias in run.yaml (#1304) 
Each model known to the system has two identifiers: 

- the `provider_resource_id` (what the provider calls it) -- e.g.,
`accounts/fireworks/models/llama-v3p1-8b-instruct`
- the `identifier` (`model_id`) under which it is registered and gets
routed to the appropriate provider.

We have so far used the HuggingFace repo alias as the standardized
identifier you can use to refer to the model. So in the above example,
we'd use `meta-llama/Llama-3.1-8B-Instruct` as the name under which it
gets registered. This makes it convenient for users to refer to these
models across providers.

However, we forgot to register the _actual_ provider model ID also. You
should be able to route via `provider_resource_id` also, of course.

This change fixes this (somewhat grave) omission.

*Note*: this change is additive -- more aliases work now compared to
before.

## Test Plan

Run the following for distro=(ollama fireworks together)
```
LLAMA_STACK_CONFIG=$distro \
   pytest -s -v tests/client-sdk/inference/test_text_inference.py \
   --inference-model=meta-llama/Llama-3.1-8B-Instruct --vision-inference-model=""
```
2025-02-27 16:39:23 -08:00

224 lines
6.1 KiB
YAML
Raw Blame History

version: '2'
image_name: nvidia
apis:
- agents
- datasetio
- eval
- inference
- 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:}
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: 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: rag-runtime
provider_type: inline::rag-runtime
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.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:
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::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
server:
port: 8321
Reference in a new issue View git blame Copy permalink