phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-20 18:48:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into agent_session_unit_test

Browse source
This commit is contained in:
Francisco Arceo 2025-08-13 08:39:53 -06:00 • committed by GitHub
commit ef5b918996
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 15 additions and 9 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:
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,
)
self.client = AsyncInferenceClient(model=config.url, provider="hf-inference")
endpoint_info = await self.client.get_endpoint_info()
self.max_tokens = endpoint_info["max_total_tokens"]
self.model_id = endpoint_info["model_id"]