phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 15:34:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updated nvidia distro with recent apis

Browse source
This commit is contained in:
Chantal D Gama Rose 2025-01-10 21:57:35 +00:00
parent 10faffcb44
commit 26a093a1d4
8 changed files with 197 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/templates/nvidia/nvidia.py
View file

@ -8,7 +8,6 @@ from pathlib import Path
from llama_stack.distribution.datatypes import ModelInput, Provider
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.nvidia import _MODEL_ALIASES
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -16,10 +15,19 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["remote::nvidia"],
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"memory": ["inline::faiss"],
"safety": ["inline::llama-guard"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
"eval": ["inline::meta-reference"],
"datasetio": ["remote::huggingface", "inline::localfs"],
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
"tool_runtime": [
"remote::brave-search",
"remote::tavily-search",
"inline::code-interpreter",
"inline::memory-runtime",
],
}
inference_provider = Provider(