phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 12:54:30 +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

18
llama_stack/providers/registry/inference.py
View file

@ -106,24 +106,6 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="hf::serverless",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi",
config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="hf::endpoint",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi",
config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(