phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-18 07:18:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add NVIDIA NIM inference adapter

Browse source
This commit is contained in:
Matthew Farrellee 2024-10-22 14:31:11 -04:00
parent ac93dd89cf
commit 2dd8c4bcb6
12 changed files with 1115 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/registry/inference.py
View file

@ -140,6 +140,15 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.adapters.inference.databricks.DatabricksImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="nvidia",
pip_packages=[], # TODO(mf): need to specify httpx if it's already a llama-stack dep?
module="llama_stack.providers.adapters.inference.nvidia",
config_class="llama_stack.providers.adapters.inference.nvidia.NVIDIAConfig",
),
),
InlineProviderSpec(
api=Api.inference,
provider_type="vllm",