phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make TGI adapter compatible with HF Inference API (#97)

Browse source
This commit is contained in:
Lucain 2024-09-25 23:08:31 +02:00 • committed by GitHub
parent 851c30597a
commit 615ed4bfbc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 122 additions and 96 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/providers/registry/inference.py
View file

@ -48,11 +48,29 @@ def available_providers() -> List[ProviderSpec]:
api=Api.inference,
adapter=AdapterSpec(
adapter_id="tgi",
pip_packages=["huggingface_hub"],
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.adapters.inference.tgi",
config_class="llama_stack.providers.adapters.inference.tgi.TGIImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_id="hf::serverless",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.adapters.inference.tgi",
config_class="llama_stack.providers.adapters.inference.tgi.InferenceAPIImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_id="hf::endpoint",
pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.adapters.inference.tgi",
config_class="llama_stack.providers.adapters.inference.tgi.InferenceEndpointImplConfig",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(