mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
dc5f05f8e6
* change ChatCompletionChunk to align with "OpenAI Chat Completions streaming API" Moving after tool_calls2 Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> add in Buffering.. Signed-off-by: Wang, Yi A <yi.a.wang@intel.com> fix: handle usage outside of stream state and add tests Simplifying everything quite a bit. Remove the unused model_dump. Clippy. Clippy ? Ruff. Uppgrade the flake for latest transformers. Upgrade after rebase. Remove potential footgun. Fix completion test. * Clippy. * Tweak for multi prompt. * Ruff. * Update the snapshot a bit. --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
16 lines
315 B
Python
16 lines
315 B
Python
import pytest
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def chat_handle(launcher):
|
|
with launcher(
|
|
"meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
) as handle:
|
|
yield handle
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
async def chat_client(chat_handle):
|
|
await chat_handle.health(300)
|
|
return chat_handle.client
|