phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 20:20:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

make TGI work well

Browse source
This commit is contained in:
Hardik Shah 2025-03-28 15:38:27 -07:00
parent e58c7f6c37
commit 021dd0d35d
9 changed files with 617 additions and 326 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tests/integration/fixtures/common.py
View file

@ -120,13 +120,16 @@ def client_with_models(
judge_model_id,
):
client = llama_stack_client
from rich.pretty import pprint
providers = [p for p in client.providers.list() if p.api == "inference"]
pprint(providers)
assert len(providers) > 0, "No inference providers found"
inference_providers = [p.provider_id for p in providers if p.provider_type != "inline::sentence-transformers"]
model_ids = {m.identifier for m in client.models.list()}
model_ids.update(m.provider_resource_id for m in client.models.list())
pprint(model_ids)
if text_model_id and text_model_id not in model_ids:
client.models.register(model_id=text_model_id, provider_id=inference_providers[0])