phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-24 06:28:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(starter)!: simplify starter distro; litellm model registry changes

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-21 10:26:30 -07:00
parent 3344d8a9e5
commit f6ba8a123d
59 changed files with 229 additions and 2304 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/tgi/config.py
View file

@ -19,7 +19,7 @@ class TGIImplConfig(BaseModel):
@classmethod
def sample_run_config(
cls,
url: str = "${env.TGI_URL}",
url: str = "${env.TGI_URL:=}",
**kwargs,
):
return {

2
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -305,6 +305,8 @@ class _HfAdapter(
class TGIAdapter(_HfAdapter):
async def initialize(self, config: TGIImplConfig) -> None:
if not config.url:
raise ValueError("You must provide a URL in run.yaml (or via the TGI_URL environment variable) to use TGI.")
log.info(f"Initializing TGI client with url={config.url}")
self.client = AsyncInferenceClient(
model=config.url,