llama-stack/llama_stack/templates/sambanova/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

175 lines
4.8 KiB
YAML

version: '2'
image_name: sambanova
apis:
- agents
- inference
- safety
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: sambanova
provider_type: remote::sambanova
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_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/sambanova}/faiss_store.db
- provider_id: chromadb
provider_type: remote::chromadb
config: {}
- provider_id: pgvector
provider_type: remote::pgvector
config: {}
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/sambanova}/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/sambanova/trace_store.db}
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: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/registry.db
models:
- metadata: {}
model_id: Meta-Llama-3.1-8B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.1-8B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.1-70B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.1-70B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.1-70B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.1-70B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.1-405B-Instruct
provider_id: sambanova
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: sambanova
provider_model_id: Meta-Llama-3.1-405B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.2-1B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.2-1B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.2-3B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-3B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.2-3B-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-3.3-70B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: sambanova
provider_model_id: Meta-Llama-3.3-70B-Instruct
model_type: llm
- metadata: {}
model_id: Llama-3.2-11B-Vision-Instruct
provider_id: sambanova
provider_model_id: Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
provider_id: sambanova
provider_model_id: Llama-3.2-11B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: Llama-3.2-90B-Vision-Instruct
provider_id: sambanova
provider_model_id: Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
provider_id: sambanova
provider_model_id: Llama-3.2-90B-Vision-Instruct
model_type: llm
- metadata: {}
model_id: Meta-Llama-Guard-3-8B
provider_id: sambanova
provider_model_id: Meta-Llama-Guard-3-8B
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-Guard-3-8B
provider_id: sambanova
provider_model_id: Meta-Llama-Guard-3-8B
model_type: llm
shields:
- shield_id: meta-llama/Llama-Guard-3-8B
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