phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 16:22:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add unsupported OpenAI mixin to all remaining inference providers

Browse source
This commit is contained in:
Ben Browning 2025-04-08 12:50:23 -04:00
parent 00c4493bda
commit 15d37fde19
7 changed files with 56 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -40,8 +40,10 @@ from llama_stack.providers.utils.inference.model_registry import (
build_hf_repo_model_entry,
)
from llama_stack.providers.utils.inference.openai_compat import (
OpenAIChatCompletionUnsupportedMixin,
OpenAICompatCompletionChoice,
OpenAICompatCompletionResponse,
OpenAICompletionUnsupportedMixin,
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
@ -69,7 +71,12 @@ def build_hf_repo_model_entries():
]
class _HfAdapter(Inference, ModelsProtocolPrivate):
class _HfAdapter(
Inference,
OpenAIChatCompletionUnsupportedMixin,
OpenAICompletionUnsupportedMixin,
ModelsProtocolPrivate,
):
client: AsyncInferenceClient
max_tokens: int
model_id: str