phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix pre-commit formatting

Browse source
This commit is contained in:
Connor Hack 2025-08-12 13:33:24 -04:00
parent 37b06dab1f
commit a53f78751d
1 changed files with 1 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -308,9 +308,7 @@ class TGIAdapter(_HfAdapter):
if not config.url: if not config.url:
raise ValueError("You must provide a URL in run.yaml (or via the TGI_URL environment variable) to use TGI.") 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}") log.info(f"Initializing TGI client with url={config.url}")
self.client = AsyncInferenceClient( self.client = AsyncInferenceClient(model=config.url, provider="hf-inference")
model=config.url,provider="hf-inference"
)
endpoint_info = await self.client.get_endpoint_info() endpoint_info = await self.client.get_endpoint_info()
self.max_tokens = endpoint_info["max_total_tokens"] self.max_tokens = endpoint_info["max_total_tokens"]
self.model_id = endpoint_info["model_id"] self.model_id = endpoint_info["model_id"]