mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-24 13:19:54 +00:00
7e30b5a466
vLLM itself can perform the embeddings generation so we don't need this extra provider. Signed-off-by: Sébastien Han <seb@redhat.com>
35 lines
782 B
YAML
35 lines
782 B
YAML
version: '2'
|
|
distribution_spec:
|
|
description: Use (an external) vLLM server for running LLM inference
|
|
providers:
|
|
inference:
|
|
- remote::vllm
|
|
vector_io:
|
|
- inline::faiss
|
|
- remote::chromadb
|
|
- remote::pgvector
|
|
safety:
|
|
- inline::llama-guard
|
|
agents:
|
|
- inline::meta-reference
|
|
eval:
|
|
- inline::meta-reference
|
|
datasetio:
|
|
- remote::huggingface
|
|
- inline::localfs
|
|
scoring:
|
|
- inline::basic
|
|
- inline::llm-as-judge
|
|
- inline::braintrust
|
|
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
|
|
additional_pip_packages:
|
|
- aiosqlite
|
|
- sqlalchemy[asyncio]
|