phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement full-passthrough in the server

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-03 14:15:20 -07:00
parent 38fd76f85c
commit 9dafa6ad94
8 changed files with 69 additions and 71 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_toolchain/inference/client.py
View file

@ -75,7 +75,7 @@ class InferenceClient(Inference):
async def run_main(host: str, port: int, stream: bool):
client = InferenceClient(f"http://{host}:{port}")
message = UserMessage(content="hello world, help me out here")
message = UserMessage(content="hello world, troll me in two-paragraphs about 42")
cprint(f"User>{message.content}", "green")
iterator = client.chat_completion(
ChatCompletionRequest(