phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 13:00:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Run distro codegen

Browse source
This commit is contained in:
Ashwin Bharambe 2025-02-20 16:53:15 -08:00
parent 8706b311ba
commit 32aa380e69
2 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/templates/nvidia/nvidia.py
View file

@ -41,9 +41,11 @@ def get_distribution_template() -> DistributionTemplate:
core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()} core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()}
default_models = [ default_models = [
ModelInput( ModelInput(
model_id=core_model_to_hf_repo[m.llama_model], model_id=core_model_to_hf_repo[m.llama_model] if m.llama_model else m.provider_model_id,
provider_model_id=m.provider_model_id, provider_model_id=m.provider_model_id,
provider_id="nvidia", provider_id="nvidia",
model_type=m.model_type,
metadata=m.metadata,
) )
for m in _MODEL_ENTRIES for m in _MODEL_ENTRIES
] ]

6
tests/client-sdk/inference/test_embedding.py
View file

@ -45,16 +45,14 @@
# #
import pytest import pytest
from llama_stack_client.types import EmbeddingsResponse from llama_stack_client.types import EmbeddingsResponse
from llama_stack_client.types.shared.interleaved_content import ( from llama_stack_client.types.shared.interleaved_content import (
TextContentItem, URL,
ImageContentItem, ImageContentItem,
ImageContentItemImage, ImageContentItemImage,
URL, TextContentItem,
) )
DUMMY_STRING = "hello" DUMMY_STRING = "hello"
DUMMY_STRING2 = "world" DUMMY_STRING2 = "world"
DUMMY_TEXT = TextContentItem(text=DUMMY_STRING, type="text") DUMMY_TEXT = TextContentItem(text=DUMMY_STRING, type="text")