phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 18:00:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add provider data keys for Cerebras, Databricks, NVIDIA, and RunPod (#3734)

Browse source 
# What does this PR do?

add provider-data key passing support to Cerebras, Databricks, NVIDIA
and RunPod

also, added missing tests for Fireworks, Anthropic, Gemini, SambaNova,
and vLLM

addresses #3517 

## Test Plan

ci w/ new tests

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
Matthew Farrellee 2025-10-27 16:09:35 -04:00 • committed by GitHub
parent 471b1b248b
commit a9b00db421
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 171 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama_stack/providers/registry/inference.py
View file

@ -61,6 +61,7 @@ def available_providers() -> list[ProviderSpec]:
pip_packages=[],
module="llama_stack.providers.remote.inference.cerebras",
config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.cerebras.config.CerebrasProviderDataValidator",
description="Cerebras inference provider for running models on Cerebras Cloud platform.",
),
RemoteProviderSpec(
@ -149,6 +150,7 @@ def available_providers() -> list[ProviderSpec]:
pip_packages=["databricks-sdk"],
module="llama_stack.providers.remote.inference.databricks",
config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.databricks.config.DatabricksProviderDataValidator",
description="Databricks inference provider for running models on Databricks' unified analytics platform.",
),
RemoteProviderSpec(
@ -158,6 +160,7 @@ def available_providers() -> list[ProviderSpec]:
pip_packages=[],
module="llama_stack.providers.remote.inference.nvidia",
config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
provider_data_validator="llama_stack.providers.remote.inference.nvidia.config.NVIDIAProviderDataValidator",
description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.",
),
RemoteProviderSpec(
@ -167,6 +170,7 @@ def available_providers() -> list[ProviderSpec]:
pip_packages=[],
module="llama_stack.providers.remote.inference.runpod",
config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.runpod.config.RunpodProviderDataValidator",
description="RunPod inference provider for running models on RunPod's cloud GPU platform.",
),
RemoteProviderSpec(