phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-04 10:10:36 +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

2
src/llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -20,6 +20,8 @@ logger = get_logger(name=__name__, category="inference::databricks")
class DatabricksInferenceAdapter(OpenAIMixin):
config: DatabricksImplConfig
provider_data_api_key_field: str = "databricks_api_token"
# source: https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models
embedding_model_metadata: dict[str, dict[str, int]] = {
"databricks-gte-large-en": {"embedding_dimension": 1024, "context_length": 8192},