mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-27 14:38:49 +00:00
776fabed9e
each *.py file in the various templates now has to use `Provider`s rather than the stringified provider_types in the DistributionTemplate. Adjust that, regenerate all templates, docs, etc. Signed-off-by: Charlie Doern <cdoern@redhat.com>
41 lines
1.1 KiB
YAML
41 lines
1.1 KiB
YAML
version: 2
|
|
distribution_spec:
|
|
description: Use NVIDIA NIM for running LLM inference, evaluation and safety
|
|
providers:
|
|
inference:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
safety:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
eval:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
post_training:
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
datasetio:
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
- provider_id: nvidia
|
|
provider_type: remote::nvidia
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
tool_runtime:
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
image_type: conda
|
|
image_name: nvidia
|
|
additional_pip_packages:
|
|
- aiosqlite
|
|
- sqlalchemy[asyncio]
|