phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use huggingface_hub inference client for TGI inference

Browse source
This commit is contained in:
Celina Hanouti 2024-09-05 18:29:04 +02:00
parent 21bedc1596
commit e5bcfdac21
6 changed files with 179 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_toolchain/core/distribution_registry.py
View file

@ -58,6 +58,16 @@ def available_distribution_specs() -> List[DistributionSpec]:
Api.memory: "meta-reference-faiss",
},
),
DistributionSpec(
distribution_id="local-plus-tgi-inference",
description="Use TGI for running LLM inference",
providers={
Api.inference: remote_provider_id("tgi"),
Api.safety: "meta-reference",
Api.agentic_system: "meta-reference",
Api.memory: "meta-reference-faiss",
},
),
]