phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 11:20:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Convert TGI to work with openai_compat

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-08 12:57:34 -07:00 • committed by Ashwin Bharambe
parent 05e73d12b3
commit ed899a5dec
6 changed files with 133 additions and 338 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/adapters/inference/together/together.py
View file

@ -48,10 +48,6 @@ class TogetherInferenceAdapter(
self.config = config
self.formatter = ChatFormat(Tokenizer.get_instance())
@property
def client(self) -> Together:
return Together(api_key=self.config.api_key)
async def initialize(self) -> None:
return
@ -91,7 +87,6 @@ class TogetherInferenceAdapter(
together_api_key = provider_data.together_api_key
client = Together(api_key=together_api_key)
# wrapper request to make it easier to pass around (internal only, not exposed to API)
request = ChatCompletionRequest(
model=model,
messages=messages,