forked from phoenix-oss/llama-stack-mirror
b2b00a216b
# What does this PR do? switch sambanova inference adaptor to LiteLLM usage to simplify integration and solve issues with current adaptor when streaming and tool calling, models and templates updated ## Test Plan pytest -s -v tests/integration/inference/test_text_inference.py --stack-config=sambanova --text-model=sambanova/Meta-Llama-3.3-70B-Instruct pytest -s -v tests/integration/inference/test_vision_inference.py --stack-config=sambanova --vision-model=sambanova/Llama-3.2-11B-Vision-Instruct
24 lines
561 B
YAML
24 lines
561 B
YAML
version: '2'
|
|
distribution_spec:
|
|
description: Use SambaNova for running LLM inference
|
|
providers:
|
|
inference:
|
|
- remote::sambanova
|
|
- inline::sentence-transformers
|
|
vector_io:
|
|
- inline::faiss
|
|
- remote::chromadb
|
|
- remote::pgvector
|
|
safety:
|
|
- inline::llama-guard
|
|
agents:
|
|
- inline::meta-reference
|
|
telemetry:
|
|
- inline::meta-reference
|
|
tool_runtime:
|
|
- remote::brave-search
|
|
- remote::tavily-search
|
|
- inline::rag-runtime
|
|
- remote::model-context-protocol
|
|
- remote::wolfram-alpha
|
|
image_type: conda
|