phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-24 02:48:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into allow-dynamic-models-nvidia

Browse source
This commit is contained in:
Matthew Farrellee 2025-07-14 19:01:28 -04:00
commit c2ab8988e6
127 changed files with 3997 additions and 3394 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/nvidia/models.py
View file

@ -11,6 +11,9 @@ from llama_stack.providers.utils.inference.model_registry import (
build_hf_repo_model_entry,
)
SAFETY_MODELS_ENTRIES = []
# https://docs.nvidia.com/nim/large-language-models/latest/supported-llm-agnostic-architectures.html
MODEL_ENTRIES = [
build_hf_repo_model_entry(
"meta/llama3-8b-instruct",
@ -99,4 +102,4 @@ MODEL_ENTRIES = [
),
# TODO(mf): how do we handle Nemotron models?
# "Llama3.1-Nemotron-51B-Instruct" -> "meta/llama-3.1-nemotron-51b-instruct",
]
] + SAFETY_MODELS_ENTRIES